WorldWideScience

Sample records for learning classification trees

  1. Deep Multi-Task Learning for Tree Genera Classification

    Science.gov (United States)

    Ko, C.; Kang, J.; Sohn, G.

    2018-05-01

    The goal for our paper is to classify tree genera using airborne Light Detection and Ranging (LiDAR) data with Convolution Neural Network (CNN) - Multi-task Network (MTN) implementation. Unlike Single-task Network (STN) where only one task is assigned to the learning outcome, MTN is a deep learning architect for learning a main task (classification of tree genera) with other tasks (in our study, classification of coniferous and deciduous) simultaneously, with shared classification features. The main contribution of this paper is to improve classification accuracy from CNN-STN to CNN-MTN. This is achieved by introducing a concurrence loss (Lcd) to the designed MTN. This term regulates the overall network performance by minimizing the inconsistencies between the two tasks. Results show that we can increase the classification accuracy from 88.7 % to 91.0 % (from STN to MTN). The second goal of this paper is to solve the problem of small training sample size by multiple-view data generation. The motivation of this goal is to address one of the most common problems in implementing deep learning architecture, the insufficient number of training data. We address this problem by simulating training dataset with multiple-view approach. The promising results from this paper are providing a basis for classifying a larger number of dataset and number of classes in the future.

  2. Boosted classification trees result in minor to modest improvement in the accuracy in classifying cardiovascular outcomes compared to conventional classification trees

    Science.gov (United States)

    Austin, Peter C; Lee, Douglas S

    2011-01-01

    Purpose: Classification trees are increasingly being used to classifying patients according to the presence or absence of a disease or health outcome. A limitation of classification trees is their limited predictive accuracy. In the data-mining and machine learning literature, boosting has been developed to improve classification. Boosting with classification trees iteratively grows classification trees in a sequence of reweighted datasets. In a given iteration, subjects that were misclassified in the previous iteration are weighted more highly than subjects that were correctly classified. Classifications from each of the classification trees in the sequence are combined through a weighted majority vote to produce a final classification. The authors' objective was to examine whether boosting improved the accuracy of classification trees for predicting outcomes in cardiovascular patients. Methods: We examined the utility of boosting classification trees for classifying 30-day mortality outcomes in patients hospitalized with either acute myocardial infarction or congestive heart failure. Results: Improvements in the misclassification rate using boosted classification trees were at best minor compared to when conventional classification trees were used. Minor to modest improvements to sensitivity were observed, with only a negligible reduction in specificity. For predicting cardiovascular mortality, boosted classification trees had high specificity, but low sensitivity. Conclusions: Gains in predictive accuracy for predicting cardiovascular outcomes were less impressive than gains in performance observed in the data mining literature. PMID:22254181

  3. Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures

    Directory of Open Access Journals (Sweden)

    Tan Zhou

    2017-12-01

    Full Text Available A plethora of information contained in full-waveform (FW Light Detection and Ranging (LiDAR data offers prospects for characterizing vegetation structures. This study aims to investigate the capacity of FW LiDAR data alone for tree species identification through the integration of waveform metrics with machine learning methods and Bayesian inference. Specifically, we first conducted automatic tree segmentation based on the waveform-based canopy height model (CHM using three approaches including TreeVaW, watershed algorithms and the combination of TreeVaW and watershed (TW algorithms. Subsequently, the Random forests (RF and Conditional inference forests (CF models were employed to identify important tree-level waveform metrics derived from three distinct sources, such as raw waveforms, composite waveforms, the waveform-based point cloud and the combined variables from these three sources. Further, we discriminated tree (gray pine, blue oak, interior live oak and shrub species through the RF, CF and Bayesian multinomial logistic regression (BMLR using important waveform metrics identified in this study. Results of the tree segmentation demonstrated that the TW algorithms outperformed other algorithms for delineating individual tree crowns. The CF model overcomes waveform metrics selection bias caused by the RF model which favors correlated metrics and enhances the accuracy of subsequent classification. We also found that composite waveforms are more informative than raw waveforms and waveform-based point cloud for characterizing tree species in our study area. Both classical machine learning methods (the RF and CF and the BMLR generated satisfactory average overall accuracy (74% for the RF, 77% for the CF and 81% for the BMLR and the BMLR slightly outperformed the other two methods. However, these three methods suffered from low individual classification accuracy for the blue oak which is prone to being misclassified as the interior live oak due

  4. Automated Decision Tree Classification of Corneal Shape

    Science.gov (United States)

    Twa, Michael D.; Parthasarathy, Srinivasan; Roberts, Cynthia; Mahmoud, Ashraf M.; Raasch, Thomas W.; Bullimore, Mark A.

    2011-01-01

    Purpose The volume and complexity of data produced during videokeratography examinations present a challenge of interpretation. As a consequence, results are often analyzed qualitatively by subjective pattern recognition or reduced to comparisons of summary indices. We describe the application of decision tree induction, an automated machine learning classification method, to discriminate between normal and keratoconic corneal shapes in an objective and quantitative way. We then compared this method with other known classification methods. Methods The corneal surface was modeled with a seventh-order Zernike polynomial for 132 normal eyes of 92 subjects and 112 eyes of 71 subjects diagnosed with keratoconus. A decision tree classifier was induced using the C4.5 algorithm, and its classification performance was compared with the modified Rabinowitz–McDonnell index, Schwiegerling’s Z3 index (Z3), Keratoconus Prediction Index (KPI), KISA%, and Cone Location and Magnitude Index using recommended classification thresholds for each method. We also evaluated the area under the receiver operator characteristic (ROC) curve for each classification method. Results Our decision tree classifier performed equal to or better than the other classifiers tested: accuracy was 92% and the area under the ROC curve was 0.97. Our decision tree classifier reduced the information needed to distinguish between normal and keratoconus eyes using four of 36 Zernike polynomial coefficients. The four surface features selected as classification attributes by the decision tree method were inferior elevation, greater sagittal depth, oblique toricity, and trefoil. Conclusions Automated decision tree classification of corneal shape through Zernike polynomials is an accurate quantitative method of classification that is interpretable and can be generated from any instrument platform capable of raw elevation data output. This method of pattern classification is extendable to other classification

  5. Fast Image Texture Classification Using Decision Trees

    Science.gov (United States)

    Thompson, David R.

    2011-01-01

    Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

  6. From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

    Science.gov (United States)

    2010-01-01

    Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for

  7. From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

    Directory of Open Access Journals (Sweden)

    Dawyndt Peter

    2010-01-01

    Full Text Available Abstract Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the

  8. From learning taxonomies to phylogenetic learning: integration of 16S rRNA gene data into FAME-based bacterial classification.

    Science.gov (United States)

    Slabbinck, Bram; Waegeman, Willem; Dawyndt, Peter; De Vos, Paul; De Baets, Bernard

    2010-01-30

    Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial

  9. Dissimilarity-based classification of anatomical tree structures

    DEFF Research Database (Denmark)

    Sørensen, Lauge; Lo, Pechin Chien Pau; Dirksen, Asger

    2011-01-01

    A novel method for classification of abnormality in anatomical tree structures is presented. A tree is classified based on direct comparisons with other trees in a dissimilarity-based classification scheme. The pair-wise dissimilarity measure between two trees is based on a linear assignment betw...

  10. Dissimilarity-based classification of anatomical tree structures

    DEFF Research Database (Denmark)

    Sørensen, Lauge Emil Borch Laurs; Lo, Pechin Chien Pau; Dirksen, Asger

    2011-01-01

    A novel method for classification of abnormality in anatomical tree structures is presented. A tree is classified based on direct comparisons with other trees in a dissimilarity-based classification scheme. The pair-wise dissimilarity measure between two trees is based on a linear assignment...

  11. The decision tree approach to classification

    Science.gov (United States)

    Wu, C.; Landgrebe, D. A.; Swain, P. H.

    1975-01-01

    A class of multistage decision tree classifiers is proposed and studied relative to the classification of multispectral remotely sensed data. The decision tree classifiers are shown to have the potential for improving both the classification accuracy and the computation efficiency. Dimensionality in pattern recognition is discussed and two theorems on the lower bound of logic computation for multiclass classification are derived. The automatic or optimization approach is emphasized. Experimental results on real data are reported, which clearly demonstrate the usefulness of decision tree classifiers.

  12. Classification and regression trees

    CERN Document Server

    Breiman, Leo; Olshen, Richard A; Stone, Charles J

    1984-01-01

    The methodology used to construct tree structured rules is the focus of this monograph. Unlike many other statistical procedures, which moved from pencil and paper to calculators, this text's use of trees was unthinkable before computers. Both the practical and theoretical sides have been developed in the authors' study of tree methods. Classification and Regression Trees reflects these two sides, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.

  13. The Hybrid of Classification Tree and Extreme Learning Machine for Permeability Prediction in Oil Reservoir

    KAUST Repository

    Prasetyo Utomo, Chandra

    2011-06-01

    Permeability is an important parameter connected with oil reservoir. Predicting the permeability could save millions of dollars. Unfortunately, petroleum engineers have faced numerous challenges arriving at cost-efficient predictions. Much work has been carried out to solve this problem. The main challenge is to handle the high range of permeability in each reservoir. For about a hundred year, mathematicians and engineers have tried to deliver best prediction models. However, none of them have produced satisfying results. In the last two decades, artificial intelligence models have been used. The current best prediction model in permeability prediction is extreme learning machine (ELM). It produces fairly good results but a clear explanation of the model is hard to come by because it is so complex. The aim of this research is to propose a way out of this complexity through the design of a hybrid intelligent model. In this proposal, the system combines classification and regression models to predict the permeability value. These are based on the well logs data. In order to handle the high range of the permeability value, a classification tree is utilized. A benefit of this innovation is that the tree represents knowledge in a clear and succinct fashion and thereby avoids the complexity of all previous models. Finally, it is important to note that the ELM is used as a final predictor. Results demonstrate that this proposed hybrid model performs better when compared with support vector machines (SVM) and ELM in term of correlation coefficient. Moreover, the classification tree model potentially leads to better communication among petroleum engineers concerning this important process and has wider implications for oil reservoir management efficiency.

  14. DIF Trees: Using Classification Trees to Detect Differential Item Functioning

    Science.gov (United States)

    Vaughn, Brandon K.; Wang, Qiu

    2010-01-01

    A nonparametric tree classification procedure is used to detect differential item functioning for items that are dichotomously scored. Classification trees are shown to be an alternative procedure to detect differential item functioning other than the use of traditional Mantel-Haenszel and logistic regression analysis. A nonparametric…

  15. Tree Classification with Fused Mobile Laser Scanning and Hyperspectral Data

    Science.gov (United States)

    Puttonen, Eetu; Jaakkola, Anttoni; Litkey, Paula; Hyyppä, Juha

    2011-01-01

    Mobile Laser Scanning data were collected simultaneously with hyperspectral data using the Finnish Geodetic Institute Sensei system. The data were tested for tree species classification. The test area was an urban garden in the City of Espoo, Finland. Point clouds representing 168 individual tree specimens of 23 tree species were determined manually. The classification of the trees was done using first only the spatial data from point clouds, then with only the spectral data obtained with a spectrometer, and finally with the combined spatial and hyperspectral data from both sensors. Two classification tests were performed: the separation of coniferous and deciduous trees, and the identification of individual tree species. All determined tree specimens were used in distinguishing coniferous and deciduous trees. A subset of 133 trees and 10 tree species was used in the tree species classification. The best classification results for the fused data were 95.8% for the separation of the coniferous and deciduous classes. The best overall tree species classification succeeded with 83.5% accuracy for the best tested fused data feature combination. The respective results for paired structural features derived from the laser point cloud were 90.5% for the separation of the coniferous and deciduous classes and 65.4% for the species classification. Classification accuracies with paired hyperspectral reflectance value data were 90.5% for the separation of coniferous and deciduous classes and 62.4% for different species. The results are among the first of their kind and they show that mobile collected fused data outperformed single-sensor data in both classification tests and by a significant margin. PMID:22163894

  16. A new tree classification system for southern hardwoods

    Science.gov (United States)

    James S. Meadows; Daniel A. Jr. Skojac

    2008-01-01

    A new tree classification system for southern hardwoods is described. The new system is based on the Putnam tree classification system, originally developed by Putnam et al., 1960, Management ond inventory of southern hardwoods, Agriculture Handbook 181, US For. Sew., Washington, DC, which consists of four tree classes: (1) preferred growing stock, (2) reserve growing...

  17. Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification.

    Science.gov (United States)

    Chen, Shizhi; Yang, Xiaodong; Tian, Yingli

    2015-09-01

    A key challenge in large-scale image classification is how to achieve efficiency in terms of both computation and memory without compromising classification accuracy. The learning-based classifiers achieve the state-of-the-art accuracies, but have been criticized for the computational complexity that grows linearly with the number of classes. The nonparametric nearest neighbor (NN)-based classifiers naturally handle large numbers of categories, but incur prohibitively expensive computation and memory costs. In this brief, we present a novel classification scheme, i.e., discriminative hierarchical K-means tree (D-HKTree), which combines the advantages of both learning-based and NN-based classifiers. The complexity of the D-HKTree only grows sublinearly with the number of categories, which is much better than the recent hierarchical support vector machines-based methods. The memory requirement is the order of magnitude less than the recent Naïve Bayesian NN-based approaches. The proposed D-HKTree classification scheme is evaluated on several challenging benchmark databases and achieves the state-of-the-art accuracies, while with significantly lower computation cost and memory requirement.

  18. Indexing Density Models for Incremental Learning and Anytime Classification on Data Streams

    DEFF Research Database (Denmark)

    Seidl, Thomas; Assent, Ira; Kranen, Philipp

    2009-01-01

    Classification of streaming data faces three basic challenges: it has to deal with huge amounts of data, the varying time between two stream data items must be used best possible (anytime classification) and additional training data must be incrementally learned (anytime learning) for applying...... to the individual object to be classified) a hierarchy of mixture densities that represent kernel density estimators at successively coarser levels. Our probability density queries together with novel classification improvement strategies provide the necessary information for very effective classification at any...... point of interruption. Moreover, we propose a novel evaluation method for anytime classification using Poisson streams and demonstrate the anytime learning performance of the Bayes tree....

  19. Active learning strategies for the deduplication of electronic patient data using classification trees.

    Science.gov (United States)

    Sariyar, M; Borg, A; Pommerening, K

    2012-10-01

    Supervised record linkage methods often require a clerical review to gain informative training data. Active learning means to actively prompt the user to label data with special characteristics in order to minimise the review costs. We conducted an empirical evaluation to investigate whether a simple active learning strategy using binary comparison patterns is sufficient or if string metrics together with a more sophisticated algorithm are necessary to achieve high accuracies with a small training set. Based on medical registry data with different numbers of attributes, we used active learning to acquire training sets for classification trees, which were then used to classify the remaining data. Active learning for binary patterns means that every distinct comparison pattern represents a stratum from which one item is sampled. Active learning for patterns consisting of the Levenshtein string metric values uses an iterative process where the most informative and representative examples are added to the training set. In this context, we extended the active learning strategy by Sarawagi and Bhamidipaty (2002). On the original data set, active learning based on binary comparison patterns leads to the best results. When dropping four or six attributes, using string metrics leads to better results. In both cases, not more than 200 manually reviewed training examples are necessary. In record linkage applications where only forename, name and birthday are available as attributes, we suggest the sophisticated active learning strategy based on string metrics in order to achieve highly accurate results. We recommend the simple strategy if more attributes are available, as in our study. In both cases, active learning significantly reduces the amount of manual involvement in training data selection compared to usual record linkage settings. Copyright © 2012 Elsevier Inc. All rights reserved.

  20. The Hybrid of Classification Tree and Extreme Learning Machine for Permeability Prediction in Oil Reservoir

    KAUST Repository

    Prasetyo Utomo, Chandra

    2011-01-01

    the permeability value. These are based on the well logs data. In order to handle the high range of the permeability value, a classification tree is utilized. A benefit of this innovation is that the tree represents knowledge in a clear and succinct fashion

  1. OmniGA: Optimized Omnivariate Decision Trees for Generalizable Classification Models

    KAUST Repository

    Magana-Mora, Arturo

    2017-06-14

    Classification problems from different domains vary in complexity, size, and imbalance of the number of samples from different classes. Although several classification models have been proposed, selecting the right model and parameters for a given classification task to achieve good performance is not trivial. Therefore, there is a constant interest in developing novel robust and efficient models suitable for a great variety of data. Here, we propose OmniGA, a framework for the optimization of omnivariate decision trees based on a parallel genetic algorithm, coupled with deep learning structure and ensemble learning methods. The performance of the OmniGA framework is evaluated on 12 different datasets taken mainly from biomedical problems and compared with the results obtained by several robust and commonly used machine-learning models with optimized parameters. The results show that OmniGA systematically outperformed these models for all the considered datasets, reducing the F score error in the range from 100% to 2.25%, compared to the best performing model. This demonstrates that OmniGA produces robust models with improved performance. OmniGA code and datasets are available at www.cbrc.kaust.edu.sa/omniga/.

  2. OmniGA: Optimized Omnivariate Decision Trees for Generalizable Classification Models

    KAUST Repository

    Magana-Mora, Arturo; Bajic, Vladimir B.

    2017-01-01

    Classification problems from different domains vary in complexity, size, and imbalance of the number of samples from different classes. Although several classification models have been proposed, selecting the right model and parameters for a given classification task to achieve good performance is not trivial. Therefore, there is a constant interest in developing novel robust and efficient models suitable for a great variety of data. Here, we propose OmniGA, a framework for the optimization of omnivariate decision trees based on a parallel genetic algorithm, coupled with deep learning structure and ensemble learning methods. The performance of the OmniGA framework is evaluated on 12 different datasets taken mainly from biomedical problems and compared with the results obtained by several robust and commonly used machine-learning models with optimized parameters. The results show that OmniGA systematically outperformed these models for all the considered datasets, reducing the F score error in the range from 100% to 2.25%, compared to the best performing model. This demonstrates that OmniGA produces robust models with improved performance. OmniGA code and datasets are available at www.cbrc.kaust.edu.sa/omniga/.

  3. Voice based gender classification using machine learning

    Science.gov (United States)

    Raahul, A.; Sapthagiri, R.; Pankaj, K.; Vijayarajan, V.

    2017-11-01

    Gender identification is one of the major problem speech analysis today. Tracing the gender from acoustic data i.e., pitch, median, frequency etc. Machine learning gives promising results for classification problem in all the research domains. There are several performance metrics to evaluate algorithms of an area. Our Comparative model algorithm for evaluating 5 different machine learning algorithms based on eight different metrics in gender classification from acoustic data. Agenda is to identify gender, with five different algorithms: Linear Discriminant Analysis (LDA), K-Nearest Neighbour (KNN), Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machine (SVM) on basis of eight different metrics. The main parameter in evaluating any algorithms is its performance. Misclassification rate must be less in classification problems, which says that the accuracy rate must be high. Location and gender of the person have become very crucial in economic markets in the form of AdSense. Here with this comparative model algorithm, we are trying to assess the different ML algorithms and find the best fit for gender classification of acoustic data.

  4. Maximizing the Diversity of Ensemble Random Forests for Tree Genera Classification Using High Density LiDAR Data

    Directory of Open Access Journals (Sweden)

    Connie Ko

    2016-08-01

    Full Text Available Recent research into improving the effectiveness of forest inventory management using airborne LiDAR data has focused on developing advanced theories in data analytics. Furthermore, supervised learning as a predictive model for classifying tree genera (and species, where possible has been gaining popularity in order to minimize this labor-intensive task. However, bottlenecks remain that hinder the immediate adoption of supervised learning methods. With supervised classification, training samples are required for learning the parameters that govern the performance of a classifier, yet the selection of training data is often subjective and the quality of such samples is critically important. For LiDAR scanning in forest environments, the quantification of data quality is somewhat abstract, normally referring to some metric related to the completeness of individual tree crowns; however, this is not an issue that has received much attention in the literature. Intuitively the choice of training samples having varying quality will affect classification accuracy. In this paper a Diversity Index (DI is proposed that characterizes the diversity of data quality (Qi among selected training samples required for constructing a classification model of tree genera. The training sample is diversified in terms of data quality as opposed to the number of samples per class. The diversified training sample allows the classifier to better learn the positive and negative instances and; therefore; has a higher classification accuracy in discriminating the “unknown” class samples from the “known” samples. Our algorithm is implemented within the Random Forests base classifiers with six derived geometric features from LiDAR data. The training sample contains three tree genera (pine; poplar; and maple and the validation samples contains four labels (pine; poplar; maple; and “unknown”. Classification accuracy improved from 72.8%; when training samples were

  5. A machine learning approach to galaxy-LSS classification - I. Imprints on halo merger trees

    Science.gov (United States)

    Hui, Jianan; Aragon, Miguel; Cui, Xinping; Flegal, James M.

    2018-04-01

    The cosmic web plays a major role in the formation and evolution of galaxies and defines, to a large extent, their properties. However, the relation between galaxies and environment is still not well understood. Here, we present a machine learning approach to study imprints of environmental effects on the mass assembly of haloes. We present a galaxy-LSS machine learning classifier based on galaxy properties sensitive to the environment. We then use the classifier to assess the relevance of each property. Correlations between galaxy properties and their cosmic environment can be used to predict galaxy membership to void/wall or filament/cluster with an accuracy of 93 per cent. Our study unveils environmental information encoded in properties of haloes not normally considered directly dependent on the cosmic environment such as merger history and complexity. Understanding the physical mechanism by which the cosmic web is imprinted in a halo can lead to significant improvements in galaxy formation models. This is accomplished by extracting features from galaxy properties and merger trees, computing feature scores for each feature and then applying support vector machine (SVM) to different feature sets. To this end, we have discovered that the shape and depth of the merger tree, formation time, and density of the galaxy are strongly associated with the cosmic environment. We describe a significant improvement in the original classification algorithm by performing LU decomposition of the distance matrix computed by the feature vectors and then using the output of the decomposition as input vectors for SVM.

  6. Transferability of decision trees for land cover classification in a ...

    African Journals Online (AJOL)

    This paper attempts to derive classification rules from training data of four Landsat-8 scenes by using the classification and regression tree (CART) implementation of the decision tree algorithm. The transferability of the ruleset was evaluated by classifying two adjacent scenes. The classification of the four mosaicked scenes ...

  7. Comparison of rule induction, decision trees and formal concept analysis approaches for classification

    Science.gov (United States)

    Kotelnikov, E. V.; Milov, V. R.

    2018-05-01

    Rule-based learning algorithms have higher transparency and easiness to interpret in comparison with neural networks and deep learning algorithms. These properties make it possible to effectively use such algorithms to solve descriptive tasks of data mining. The choice of an algorithm depends also on its ability to solve predictive tasks. The article compares the quality of the solution of the problems with binary and multiclass classification based on the experiments with six datasets from the UCI Machine Learning Repository. The authors investigate three algorithms: Ripper (rule induction), C4.5 (decision trees), In-Close (formal concept analysis). The results of the experiments show that In-Close demonstrates the best quality of classification in comparison with Ripper and C4.5, however the latter two generate more compact rule sets.

  8. Phylogenetic classification and the universal tree.

    Science.gov (United States)

    Doolittle, W F

    1999-06-25

    From comparative analyses of the nucleotide sequences of genes encoding ribosomal RNAs and several proteins, molecular phylogeneticists have constructed a "universal tree of life," taking it as the basis for a "natural" hierarchical classification of all living things. Although confidence in some of the tree's early branches has recently been shaken, new approaches could still resolve many methodological uncertainties. More challenging is evidence that most archaeal and bacterial genomes (and the inferred ancestral eukaryotic nuclear genome) contain genes from multiple sources. If "chimerism" or "lateral gene transfer" cannot be dismissed as trivial in extent or limited to special categories of genes, then no hierarchical universal classification can be taken as natural. Molecular phylogeneticists will have failed to find the "true tree," not because their methods are inadequate or because they have chosen the wrong genes, but because the history of life cannot properly be represented as a tree. However, taxonomies based on molecular sequences will remain indispensable, and understanding of the evolutionary process will ultimately be enriched, not impoverished.

  9. Comprehensive decision tree models in bioinformatics.

    Directory of Open Access Journals (Sweden)

    Gregor Stiglic

    Full Text Available PURPOSE: Classification is an important and widely used machine learning technique in bioinformatics. Researchers and other end-users of machine learning software often prefer to work with comprehensible models where knowledge extraction and explanation of reasoning behind the classification model are possible. METHODS: This paper presents an extension to an existing machine learning environment and a study on visual tuning of decision tree classifiers. The motivation for this research comes from the need to build effective and easily interpretable decision tree models by so called one-button data mining approach where no parameter tuning is needed. To avoid bias in classification, no classification performance measure is used during the tuning of the model that is constrained exclusively by the dimensions of the produced decision tree. RESULTS: The proposed visual tuning of decision trees was evaluated on 40 datasets containing classical machine learning problems and 31 datasets from the field of bioinformatics. Although we did not expected significant differences in classification performance, the results demonstrate a significant increase of accuracy in less complex visually tuned decision trees. In contrast to classical machine learning benchmarking datasets, we observe higher accuracy gains in bioinformatics datasets. Additionally, a user study was carried out to confirm the assumption that the tree tuning times are significantly lower for the proposed method in comparison to manual tuning of the decision tree. CONCLUSIONS: The empirical results demonstrate that by building simple models constrained by predefined visual boundaries, one not only achieves good comprehensibility, but also very good classification performance that does not differ from usually more complex models built using default settings of the classical decision tree algorithm. In addition, our study demonstrates the suitability of visually tuned decision trees for datasets

  10. Comprehensive decision tree models in bioinformatics.

    Science.gov (United States)

    Stiglic, Gregor; Kocbek, Simon; Pernek, Igor; Kokol, Peter

    2012-01-01

    Classification is an important and widely used machine learning technique in bioinformatics. Researchers and other end-users of machine learning software often prefer to work with comprehensible models where knowledge extraction and explanation of reasoning behind the classification model are possible. This paper presents an extension to an existing machine learning environment and a study on visual tuning of decision tree classifiers. The motivation for this research comes from the need to build effective and easily interpretable decision tree models by so called one-button data mining approach where no parameter tuning is needed. To avoid bias in classification, no classification performance measure is used during the tuning of the model that is constrained exclusively by the dimensions of the produced decision tree. The proposed visual tuning of decision trees was evaluated on 40 datasets containing classical machine learning problems and 31 datasets from the field of bioinformatics. Although we did not expected significant differences in classification performance, the results demonstrate a significant increase of accuracy in less complex visually tuned decision trees. In contrast to classical machine learning benchmarking datasets, we observe higher accuracy gains in bioinformatics datasets. Additionally, a user study was carried out to confirm the assumption that the tree tuning times are significantly lower for the proposed method in comparison to manual tuning of the decision tree. The empirical results demonstrate that by building simple models constrained by predefined visual boundaries, one not only achieves good comprehensibility, but also very good classification performance that does not differ from usually more complex models built using default settings of the classical decision tree algorithm. In addition, our study demonstrates the suitability of visually tuned decision trees for datasets with binary class attributes and a high number of possibly

  11. Multi-test decision tree and its application to microarray data classification.

    Science.gov (United States)

    Czajkowski, Marcin; Grześ, Marek; Kretowski, Marek

    2014-05-01

    The desirable property of tools used to investigate biological data is easy to understand models and predictive decisions. Decision trees are particularly promising in this regard due to their comprehensible nature that resembles the hierarchical process of human decision making. However, existing algorithms for learning decision trees have tendency to underfit gene expression data. The main aim of this work is to improve the performance and stability of decision trees with only a small increase in their complexity. We propose a multi-test decision tree (MTDT); our main contribution is the application of several univariate tests in each non-terminal node of the decision tree. We also search for alternative, lower-ranked features in order to obtain more stable and reliable predictions. Experimental validation was performed on several real-life gene expression datasets. Comparison results with eight classifiers show that MTDT has a statistically significantly higher accuracy than popular decision tree classifiers, and it was highly competitive with ensemble learning algorithms. The proposed solution managed to outperform its baseline algorithm on 14 datasets by an average 6%. A study performed on one of the datasets showed that the discovered genes used in the MTDT classification model are supported by biological evidence in the literature. This paper introduces a new type of decision tree which is more suitable for solving biological problems. MTDTs are relatively easy to analyze and much more powerful in modeling high dimensional microarray data than their popular counterparts. Copyright © 2014 Elsevier B.V. All rights reserved.

  12. PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

    Energy Technology Data Exchange (ETDEWEB)

    Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K. [Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT (United Kingdom); McEwen, Jason D., E-mail: dr.michelle.lochner@gmail.com [Mullard Space Science Laboratory, University College London, Surrey RH5 6NT (United Kingdom)

    2016-08-01

    Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

  13. PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

    International Nuclear Information System (INIS)

    Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.; McEwen, Jason D.

    2016-01-01

    Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

  14. Predicting Battle Outcomes with Classification Trees

    National Research Council Canada - National Science Library

    Coban, Muzaffer

    2001-01-01

    ... from the actual battlefield, The models built by using classification trees reveal that the objective variables alone cannot explain the outcome of battles, Relative factors, such as leadership, have deep...

  15. Lidar-based individual tree species classification using convolutional neural network

    Science.gov (United States)

    Mizoguchi, Tomohiro; Ishii, Akira; Nakamura, Hiroyuki; Inoue, Tsuyoshi; Takamatsu, Hisashi

    2017-06-01

    Terrestrial lidar is commonly used for detailed documentation in the field of forest inventory investigation. Recent improvements of point cloud processing techniques enabled efficient and precise computation of an individual tree shape parameters, such as breast-height diameter, height, and volume. However, tree species are manually specified by skilled workers to date. Previous works for automatic tree species classification mainly focused on aerial or satellite images, and few works have been reported for classification techniques using ground-based sensor data. Several candidate sensors can be considered for classification, such as RGB or multi/hyper spectral cameras. Above all candidates, we use terrestrial lidar because it can obtain high resolution point cloud in the dark forest. We selected bark texture for the classification criteria, since they clearly represent unique characteristics of each tree and do not change their appearance under seasonable variation and aged deterioration. In this paper, we propose a new method for automatic individual tree species classification based on terrestrial lidar using Convolutional Neural Network (CNN). The key component is the creation step of a depth image which well describe the characteristics of each species from a point cloud. We focus on Japanese cedar and cypress which cover the large part of domestic forest. Our experimental results demonstrate the effectiveness of our proposed method.

  16. A ROUGH SET DECISION TREE BASED MLP-CNN FOR VERY HIGH RESOLUTION REMOTELY SENSED IMAGE CLASSIFICATION

    Directory of Open Access Journals (Sweden)

    C. Zhang

    2017-09-01

    Full Text Available Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP, which are unable to exploit abundant spatial details within VHR images. This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.

  17. Using methods from the data mining and machine learning literature for disease classification and prediction: A case study examining classification of heart failure sub-types

    Science.gov (United States)

    Austin, Peter C.; Tu, Jack V.; Ho, Jennifer E.; Levy, Daniel; Lee, Douglas S.

    2014-01-01

    Objective Physicians classify patients into those with or without a specific disease. Furthermore, there is often interest in classifying patients according to disease etiology or subtype. Classification trees are frequently used to classify patients according to the presence or absence of a disease. However, classification trees can suffer from limited accuracy. In the data-mining and machine learning literature, alternate classification schemes have been developed. These include bootstrap aggregation (bagging), boosting, random forests, and support vector machines. Study design and Setting We compared the performance of these classification methods with those of conventional classification trees to classify patients with heart failure according to the following sub-types: heart failure with preserved ejection fraction (HFPEF) vs. heart failure with reduced ejection fraction (HFREF). We also compared the ability of these methods to predict the probability of the presence of HFPEF with that of conventional logistic regression. Results We found that modern, flexible tree-based methods from the data mining literature offer substantial improvement in prediction and classification of heart failure sub-type compared to conventional classification and regression trees. However, conventional logistic regression had superior performance for predicting the probability of the presence of HFPEF compared to the methods proposed in the data mining literature. Conclusion The use of tree-based methods offers superior performance over conventional classification and regression trees for predicting and classifying heart failure subtypes in a population-based sample of patients from Ontario. However, these methods do not offer substantial improvements over logistic regression for predicting the presence of HFPEF. PMID:23384592

  18. A novel transferable individual tree crown delineation model based on Fishing Net Dragging and boundary classification

    Science.gov (United States)

    Liu, Tao; Im, Jungho; Quackenbush, Lindi J.

    2015-12-01

    This study provides a novel approach to individual tree crown delineation (ITCD) using airborne Light Detection and Ranging (LiDAR) data in dense natural forests using two main steps: crown boundary refinement based on a proposed Fishing Net Dragging (FiND) method, and segment merging based on boundary classification. FiND starts with approximate tree crown boundaries derived using a traditional watershed method with Gaussian filtering and refines these boundaries using an algorithm that mimics how a fisherman drags a fishing net. Random forest machine learning is then used to classify boundary segments into two classes: boundaries between trees and boundaries between branches that belong to a single tree. Three groups of LiDAR-derived features-two from the pseudo waveform generated along with crown boundaries and one from a canopy height model (CHM)-were used in the classification. The proposed ITCD approach was tested using LiDAR data collected over a mountainous region in the Adirondack Park, NY, USA. Overall accuracy of boundary classification was 82.4%. Features derived from the CHM were generally more important in the classification than the features extracted from the pseudo waveform. A comprehensive accuracy assessment scheme for ITCD was also introduced by considering both area of crown overlap and crown centroids. Accuracy assessment using this new scheme shows the proposed ITCD achieved 74% and 78% as overall accuracy, respectively, for deciduous and mixed forest.

  19. On Internet Traffic Classification: A Two-Phased Machine Learning Approach

    Directory of Open Access Journals (Sweden)

    Taimur Bakhshi

    2016-01-01

    Full Text Available Traffic classification utilizing flow measurement enables operators to perform essential network management. Flow accounting methods such as NetFlow are, however, considered inadequate for classification requiring additional packet-level information, host behaviour analysis, and specialized hardware limiting their practical adoption. This paper aims to overcome these challenges by proposing two-phased machine learning classification mechanism with NetFlow as input. The individual flow classes are derived per application through k-means and are further used to train a C5.0 decision tree classifier. As part of validation, the initial unsupervised phase used flow records of fifteen popular Internet applications that were collected and independently subjected to k-means clustering to determine unique flow classes generated per application. The derived flow classes were afterwards used to train and test a supervised C5.0 based decision tree. The resulting classifier reported an average accuracy of 92.37% on approximately 3.4 million test cases increasing to 96.67% with adaptive boosting. The classifier specificity factor which accounted for differentiating content specific from supplementary flows ranged between 98.37% and 99.57%. Furthermore, the computational performance and accuracy of the proposed methodology in comparison with similar machine learning techniques lead us to recommend its extension to other applications in achieving highly granular real-time traffic classification.

  20. Object-based methods for individual tree identification and tree species classification from high-spatial resolution imagery

    Science.gov (United States)

    Wang, Le

    2003-10-01

    Modern forest management poses an increasing need for detailed knowledge of forest information at different spatial scales. At the forest level, the information for tree species assemblage is desired whereas at or below the stand level, individual tree related information is preferred. Remote Sensing provides an effective tool to extract the above information at multiple spatial scales in the continuous time domain. To date, the increasing volume and readily availability of high-spatial-resolution data have lead to a much wider application of remotely sensed products. Nevertheless, to make effective use of the improving spatial resolution, conventional pixel-based classification methods are far from satisfactory. Correspondingly, developing object-based methods becomes a central challenge for researchers in the field of Remote Sensing. This thesis focuses on the development of methods for accurate individual tree identification and tree species classification. We develop a method in which individual tree crown boundaries and treetop locations are derived under a unified framework. We apply a two-stage approach with edge detection followed by marker-controlled watershed segmentation. Treetops are modeled from radiometry and geometry aspects. Specifically, treetops are assumed to be represented by local radiation maxima and to be located near the center of the tree-crown. As a result, a marker image was created from the derived treetop to guide a watershed segmentation to further differentiate overlapping trees and to produce a segmented image comprised of individual tree crowns. The image segmentation method developed achieves a promising result for a 256 x 256 CASI image. Then further effort is made to extend our methods to the multiscales which are constructed from a wavelet decomposition. A scale consistency and geometric consistency are designed to examine the gradients along the scale-space for the purpose of separating true crown boundary from unwanted

  1. Building classification trees to explain the radioactive contamination levels of the plants

    International Nuclear Information System (INIS)

    Briand, B.

    2008-04-01

    The objective of this thesis is the development of a method allowing the identification of factors leading to various radioactive contamination levels of the plants. The methodology suggested is based on the use of a radioecological transfer model of the radionuclides through the environment (A.S.T.R.A.L. computer code) and a classification-tree method. Particularly, to avoid the instability problems of classification trees and to preserve the tree structure, a node level stabilizing technique is used. Empirical comparisons are carried out between classification trees built by this method (called R.E.N. method) and those obtained by the C.A.R.T. method. A similarity measure is defined to compare the structure of two classification trees. This measure is used to study the stabilizing performance of the R.E.N. method. The methodology suggested is applied to a simplified contamination scenario. By the results obtained, we can identify the main variables responsible of the various radioactive contamination levels of four leafy-vegetables (lettuce, cabbage, spinach and leek). Some extracted rules from these classification trees can be usable in a post-accidental context. (author)

  2. Time Series of Images to Improve Tree Species Classification

    Science.gov (United States)

    Miyoshi, G. T.; Imai, N. N.; de Moraes, M. V. A.; Tommaselli, A. M. G.; Näsi, R.

    2017-10-01

    Tree species classification provides valuable information to forest monitoring and management. The high floristic variation of the tree species appears as a challenging issue in the tree species classification because the vegetation characteristics changes according to the season. To help to monitor this complex environment, the imaging spectroscopy has been largely applied since the development of miniaturized sensors attached to Unmanned Aerial Vehicles (UAV). Considering the seasonal changes in forests and the higher spectral and spatial resolution acquired with sensors attached to UAV, we present the use of time series of images to classify four tree species. The study area is an Atlantic Forest area located in the western part of São Paulo State. Images were acquired in August 2015 and August 2016, generating three data sets of images: only with the image spectra of 2015; only with the image spectra of 2016; with the layer stacking of images from 2015 and 2016. Four tree species were classified using Spectral angle mapper (SAM), Spectral information divergence (SID) and Random Forest (RF). The results showed that SAM and SID caused an overfitting of the data whereas RF showed better results and the use of the layer stacking improved the classification achieving a kappa coefficient of 18.26 %.

  3. An Active Learning Framework for Hyperspectral Image Classification Using Hierarchical Segmentation

    Science.gov (United States)

    Zhang, Zhou; Pasolli, Edoardo; Crawford, Melba M.; Tilton, James C.

    2015-01-01

    Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral-spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral-spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

  4. Meta-learning in decision tree induction

    CERN Document Server

    Grąbczewski, Krzysztof

    2014-01-01

    The book focuses on different variants of decision tree induction but also describes  the meta-learning approach in general which is applicable to other types of machine learning algorithms. The book discusses different variants of decision tree induction and represents a useful source of information to readers wishing to review some of the techniques used in decision tree learning, as well as different ensemble methods that involve decision trees. It is shown that the knowledge of different components used within decision tree learning needs to be systematized to enable the system to generate and evaluate different variants of machine learning algorithms with the aim of identifying the top-most performers or potentially the best one. A unified view of decision tree learning enables to emulate different decision tree algorithms simply by setting certain parameters. As meta-learning requires running many different processes with the aim of obtaining performance results, a detailed description of the experimen...

  5. Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

    CSIR Research Space (South Africa)

    Adelabu, S

    2013-11-01

    Full Text Available in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples. We performed...

  6. An Efficient Ensemble Learning Method for Gene Microarray Classification

    Directory of Open Access Journals (Sweden)

    Alireza Osareh

    2013-01-01

    Full Text Available The gene microarray analysis and classification have demonstrated an effective way for the effective diagnosis of diseases and cancers. However, it has been also revealed that the basic classification techniques have intrinsic drawbacks in achieving accurate gene classification and cancer diagnosis. On the other hand, classifier ensembles have received increasing attention in various applications. Here, we address the gene classification issue using RotBoost ensemble methodology. This method is a combination of Rotation Forest and AdaBoost techniques which in turn preserve both desirable features of an ensemble architecture, that is, accuracy and diversity. To select a concise subset of informative genes, 5 different feature selection algorithms are considered. To assess the efficiency of the RotBoost, other nonensemble/ensemble techniques including Decision Trees, Support Vector Machines, Rotation Forest, AdaBoost, and Bagging are also deployed. Experimental results have revealed that the combination of the fast correlation-based feature selection method with ICA-based RotBoost ensemble is highly effective for gene classification. In fact, the proposed method can create ensemble classifiers which outperform not only the classifiers produced by the conventional machine learning but also the classifiers generated by two widely used conventional ensemble learning methods, that is, Bagging and AdaBoost.

  7. Multi-level discriminative dictionary learning with application to large scale image classification.

    Science.gov (United States)

    Shen, Li; Sun, Gang; Huang, Qingming; Wang, Shuhui; Lin, Zhouchen; Wu, Enhua

    2015-10-01

    The sparse coding technique has shown flexibility and capability in image representation and analysis. It is a powerful tool in many visual applications. Some recent work has shown that incorporating the properties of task (such as discrimination for classification task) into dictionary learning is effective for improving the accuracy. However, the traditional supervised dictionary learning methods suffer from high computation complexity when dealing with large number of categories, making them less satisfactory in large scale applications. In this paper, we propose a novel multi-level discriminative dictionary learning method and apply it to large scale image classification. Our method takes advantage of hierarchical category correlation to encode multi-level discriminative information. Each internal node of the category hierarchy is associated with a discriminative dictionary and a classification model. The dictionaries at different layers are learnt to capture the information of different scales. Moreover, each node at lower layers also inherits the dictionary of its parent, so that the categories at lower layers can be described with multi-scale information. The learning of dictionaries and associated classification models is jointly conducted by minimizing an overall tree loss. The experimental results on challenging data sets demonstrate that our approach achieves excellent accuracy and competitive computation cost compared with other sparse coding methods for large scale image classification.

  8. A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

    Directory of Open Access Journals (Sweden)

    Zekić-Sušac Marijana

    2014-09-01

    Full Text Available Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.

  9. The process and utility of classification and regression tree methodology in nursing research.

    Science.gov (United States)

    Kuhn, Lisa; Page, Karen; Ward, John; Worrall-Carter, Linda

    2014-06-01

    This paper presents a discussion of classification and regression tree analysis and its utility in nursing research. Classification and regression tree analysis is an exploratory research method used to illustrate associations between variables not suited to traditional regression analysis. Complex interactions are demonstrated between covariates and variables of interest in inverted tree diagrams. Discussion paper. English language literature was sourced from eBooks, Medline Complete and CINAHL Plus databases, Google and Google Scholar, hard copy research texts and retrieved reference lists for terms including classification and regression tree* and derivatives and recursive partitioning from 1984-2013. Classification and regression tree analysis is an important method used to identify previously unknown patterns amongst data. Whilst there are several reasons to embrace this method as a means of exploratory quantitative research, issues regarding quality of data as well as the usefulness and validity of the findings should be considered. Classification and regression tree analysis is a valuable tool to guide nurses to reduce gaps in the application of evidence to practice. With the ever-expanding availability of data, it is important that nurses understand the utility and limitations of the research method. Classification and regression tree analysis is an easily interpreted method for modelling interactions between health-related variables that would otherwise remain obscured. Knowledge is presented graphically, providing insightful understanding of complex and hierarchical relationships in an accessible and useful way to nursing and other health professions. © 2013 The Authors. Journal of Advanced Nursing Published by John Wiley & Sons Ltd.

  10. Neuropsychological Test Selection for Cognitive Impairment Classification: A Machine Learning Approach

    Science.gov (United States)

    Williams, Jennifer A.; Schmitter-Edgecombe, Maureen; Cook, Diane J.

    2016-01-01

    Introduction Reducing the amount of testing required to accurately detect cognitive impairment is clinically relevant. The aim of this research was to determine the fewest number of clinical measures required to accurately classify participants as healthy older adult, mild cognitive impairment (MCI) or dementia using a suite of classification techniques. Methods Two variable selection machine learning models (i.e., naive Bayes, decision tree), a logistic regression, and two participant datasets (i.e., clinical diagnosis, clinical dementia rating; CDR) were explored. Participants classified using clinical diagnosis criteria included 52 individuals with dementia, 97 with MCI, and 161 cognitively healthy older adults. Participants classified using CDR included 154 individuals CDR = 0, 93 individuals with CDR = 0.5, and 25 individuals with CDR = 1.0+. Twenty-seven demographic, psychological, and neuropsychological variables were available for variable selection. Results No significant difference was observed between naive Bayes, decision tree, and logistic regression models for classification of both clinical diagnosis and CDR datasets. Participant classification (70.0 – 99.1%), geometric mean (60.9 – 98.1%), sensitivity (44.2 – 100%), and specificity (52.7 – 100%) were generally satisfactory. Unsurprisingly, the MCI/CDR = 0.5 participant group was the most challenging to classify. Through variable selection only 2 – 9 variables were required for classification and varied between datasets in a clinically meaningful way. Conclusions The current study results reveal that machine learning techniques can accurately classifying cognitive impairment and reduce the number of measures required for diagnosis. PMID:26332171

  11. FACET CLASSIFICATIONS OF E-LEARNING TOOLS

    Directory of Open Access Journals (Sweden)

    Olena Yu. Balalaieva

    2013-12-01

    Full Text Available The article deals with the classification of e-learning tools based on the facet method, which suggests the separation of the parallel set of objects into independent classification groups; at the same time it is not assumed rigid classification structure and pre-built finite groups classification groups are formed by a combination of values taken from the relevant facets. An attempt to systematize the existing classification of e-learning tools from the standpoint of classification theory is made for the first time. Modern Ukrainian and foreign facet classifications of e-learning tools are described; their positive and negative features compared to classifications based on a hierarchical method are analyzed. The original author's facet classification of e-learning tools is proposed.

  12. Improving Land Use/Land Cover Classification by Integrating Pixel Unmixing and Decision Tree Methods

    Directory of Open Access Journals (Sweden)

    Chao Yang

    2017-11-01

    Full Text Available Decision tree classification is one of the most efficient methods for obtaining land use/land cover (LULC information from remotely sensed imageries. However, traditional decision tree classification methods cannot effectively eliminate the influence of mixed pixels. This study aimed to integrate pixel unmixing and decision tree to improve LULC classification by removing mixed pixel influence. The abundance and minimum noise fraction (MNF results that were obtained from mixed pixel decomposition were added to decision tree multi-features using a three-dimensional (3D Terrain model, which was created using an image fusion digital elevation model (DEM, to select training samples (ROIs, and improve ROI separability. A Landsat-8 OLI image of the Yunlong Reservoir Basin in Kunming was used to test this proposed method. Study results showed that the Kappa coefficient and the overall accuracy of integrated pixel unmixing and decision tree method increased by 0.093% and 10%, respectively, as compared with the original decision tree method. This proposed method could effectively eliminate the influence of mixed pixels and improve the accuracy in complex LULC classifications.

  13. Decision tree methods: applications for classification and prediction.

    Science.gov (United States)

    Song, Yan-Yan; Lu, Ying

    2015-04-25

    Decision tree methodology is a commonly used data mining method for establishing classification systems based on multiple covariates or for developing prediction algorithms for a target variable. This method classifies a population into branch-like segments that construct an inverted tree with a root node, internal nodes, and leaf nodes. The algorithm is non-parametric and can efficiently deal with large, complicated datasets without imposing a complicated parametric structure. When the sample size is large enough, study data can be divided into training and validation datasets. Using the training dataset to build a decision tree model and a validation dataset to decide on the appropriate tree size needed to achieve the optimal final model. This paper introduces frequently used algorithms used to develop decision trees (including CART, C4.5, CHAID, and QUEST) and describes the SPSS and SAS programs that can be used to visualize tree structure.

  14. Vlsi implementation of flexible architecture for decision tree classification in data mining

    Science.gov (United States)

    Sharma, K. Venkatesh; Shewandagn, Behailu; Bhukya, Shankar Nayak

    2017-07-01

    The Data mining algorithms have become vital to researchers in science, engineering, medicine, business, search and security domains. In recent years, there has been a terrific raise in the size of the data being collected and analyzed. Classification is the main difficulty faced in data mining. In a number of the solutions developed for this problem, most accepted one is Decision Tree Classification (DTC) that gives high precision while handling very large amount of data. This paper presents VLSI implementation of flexible architecture for Decision Tree classification in data mining using c4.5 algorithm.

  15. Working memory supports inference learning just like classification learning.

    Science.gov (United States)

    Craig, Stewart; Lewandowsky, Stephan

    2013-08-01

    Recent research has found a positive relationship between people's working memory capacity (WMC) and their speed of category learning. To date, only classification-learning tasks have been considered, in which people learn to assign category labels to objects. It is unknown whether learning to make inferences about category features might also be related to WMC. We report data from a study in which 119 participants undertook classification learning and inference learning, and completed a series of WMC tasks. Working memory capacity was positively related to people's classification and inference learning performance.

  16. Modeling time-to-event (survival) data using classification tree analysis.

    Science.gov (United States)

    Linden, Ariel; Yarnold, Paul R

    2017-12-01

    Time to the occurrence of an event is often studied in health research. Survival analysis differs from other designs in that follow-up times for individuals who do not experience the event by the end of the study (called censored) are accounted for in the analysis. Cox regression is the standard method for analysing censored data, but the assumptions required of these models are easily violated. In this paper, we introduce classification tree analysis (CTA) as a flexible alternative for modelling censored data. Classification tree analysis is a "decision-tree"-like classification model that provides parsimonious, transparent (ie, easy to visually display and interpret) decision rules that maximize predictive accuracy, derives exact P values via permutation tests, and evaluates model cross-generalizability. Using empirical data, we identify all statistically valid, reproducible, longitudinally consistent, and cross-generalizable CTA survival models and then compare their predictive accuracy to estimates derived via Cox regression and an unadjusted naïve model. Model performance is assessed using integrated Brier scores and a comparison between estimated survival curves. The Cox regression model best predicts average incidence of the outcome over time, whereas CTA survival models best predict either relatively high, or low, incidence of the outcome over time. Classification tree analysis survival models offer many advantages over Cox regression, such as explicit maximization of predictive accuracy, parsimony, statistical robustness, and transparency. Therefore, researchers interested in accurate prognoses and clear decision rules should consider developing models using the CTA-survival framework. © 2017 John Wiley & Sons, Ltd.

  17. Crown-Level Tree Species Classification Using Integrated Airborne Hyperspectral and LIDAR Remote Sensing Data

    Science.gov (United States)

    Wang, Z.; Wu, J.; Wang, Y.; Kong, X.; Bao, H.; Ni, Y.; Ma, L.; Jin, J.

    2018-05-01

    Mapping tree species is essential for sustainable planning as well as to improve our understanding of the role of different trees as different ecological service. However, crown-level tree species automatic classification is a challenging task due to the spectral similarity among diversified tree species, fine-scale spatial variation, shadow, and underlying objects within a crown. Advanced remote sensing data such as airborne Light Detection and Ranging (LiDAR) and hyperspectral imagery offer a great potential opportunity to derive crown spectral, structure and canopy physiological information at the individual crown scale, which can be useful for mapping tree species. In this paper, an innovative approach was developed for tree species classification at the crown level. The method utilized LiDAR data for individual tree crown delineation and morphological structure extraction, and Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery for pure crown-scale spectral extraction. Specifically, four steps were include: 1) A weighted mean filtering method was developed to improve the accuracy of the smoothed Canopy Height Model (CHM) derived from LiDAR data; 2) The marker-controlled watershed segmentation algorithm was, therefore, also employed to delineate the tree-level canopy from the CHM image in this study, and then individual tree height and tree crown were calculated according to the delineated crown; 3) Spectral features within 3 × 3 neighborhood regions centered on the treetops detected by the treetop detection algorithm were derived from the spectrally normalized CASI imagery; 4) The shape characteristics related to their crown diameters and heights were established, and different crown-level tree species were classified using the combination of spectral and shape characteristics. Analysis of results suggests that the developed classification strategy in this paper (OA = 85.12 %, Kc = 0.90) performed better than LiDAR-metrics method (OA = 79

  18. Aneurysmal subarachnoid hemorrhage prognostic decision-making algorithm using classification and regression tree analysis.

    Science.gov (United States)

    Lo, Benjamin W Y; Fukuda, Hitoshi; Angle, Mark; Teitelbaum, Jeanne; Macdonald, R Loch; Farrokhyar, Forough; Thabane, Lehana; Levine, Mitchell A H

    2016-01-01

    Classification and regression tree analysis involves the creation of a decision tree by recursive partitioning of a dataset into more homogeneous subgroups. Thus far, there is scarce literature on using this technique to create clinical prediction tools for aneurysmal subarachnoid hemorrhage (SAH). The classification and regression tree analysis technique was applied to the multicenter Tirilazad database (3551 patients) in order to create the decision-making algorithm. In order to elucidate prognostic subgroups in aneurysmal SAH, neurologic, systemic, and demographic factors were taken into account. The dependent variable used for analysis was the dichotomized Glasgow Outcome Score at 3 months. Classification and regression tree analysis revealed seven prognostic subgroups. Neurological grade, occurrence of post-admission stroke, occurrence of post-admission fever, and age represented the explanatory nodes of this decision tree. Split sample validation revealed classification accuracy of 79% for the training dataset and 77% for the testing dataset. In addition, the occurrence of fever at 1-week post-aneurysmal SAH is associated with increased odds of post-admission stroke (odds ratio: 1.83, 95% confidence interval: 1.56-2.45, P tree was generated, which serves as a prediction tool to guide bedside prognostication and clinical treatment decision making. This prognostic decision-making algorithm also shed light on the complex interactions between a number of risk factors in determining outcome after aneurysmal SAH.

  19. Univariate decision tree induction using maximum margin classification

    OpenAIRE

    Yıldız, Olcay Taner

    2012-01-01

    In many pattern recognition applications, first decision trees are used due to their simplicity and easily interpretable nature. In this paper, we propose a new decision tree learning algorithm called univariate margin tree where, for each continuous attribute, the best split is found using convex optimization. Our simulation results on 47 data sets show that the novel margin tree classifier performs at least as good as C4.5 and linear discriminant tree (LDT) with a similar time complexity. F...

  20. Spatial prediction of landslides using a hybrid machine learning approach based on Random Subspace and Classification and Regression Trees

    Science.gov (United States)

    Pham, Binh Thai; Prakash, Indra; Tien Bui, Dieu

    2018-02-01

    A hybrid machine learning approach of Random Subspace (RSS) and Classification And Regression Trees (CART) is proposed to develop a model named RSSCART for spatial prediction of landslides. This model is a combination of the RSS method which is known as an efficient ensemble technique and the CART which is a state of the art classifier. The Luc Yen district of Yen Bai province, a prominent landslide prone area of Viet Nam, was selected for the model development. Performance of the RSSCART model was evaluated through the Receiver Operating Characteristic (ROC) curve, statistical analysis methods, and the Chi Square test. Results were compared with other benchmark landslide models namely Support Vector Machines (SVM), single CART, Naïve Bayes Trees (NBT), and Logistic Regression (LR). In the development of model, ten important landslide affecting factors related with geomorphology, geology and geo-environment were considered namely slope angles, elevation, slope aspect, curvature, lithology, distance to faults, distance to rivers, distance to roads, and rainfall. Performance of the RSSCART model (AUC = 0.841) is the best compared with other popular landslide models namely SVM (0.835), single CART (0.822), NBT (0.821), and LR (0.723). These results indicate that performance of the RSSCART is a promising method for spatial landslide prediction.

  1. Discriminant forest classification method and system

    Science.gov (United States)

    Chen, Barry Y.; Hanley, William G.; Lemmond, Tracy D.; Hiller, Lawrence J.; Knapp, David A.; Mugge, Marshall J.

    2012-11-06

    A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

  2. An object-oriented classification method of high resolution imagery based on improved AdaTree

    International Nuclear Information System (INIS)

    Xiaohe, Zhang; Liang, Zhai; Jixian, Zhang; Huiyong, Sang

    2014-01-01

    With the popularity of the application using high spatial resolution remote sensing image, more and more studies paid attention to object-oriented classification on image segmentation as well as automatic classification after image segmentation. This paper proposed a fast method of object-oriented automatic classification. First, edge-based or FNEA-based segmentation was used to identify image objects and the values of most suitable attributes of image objects for classification were calculated. Then a certain number of samples from the image objects were selected as training data for improved AdaTree algorithm to get classification rules. Finally, the image objects could be classified easily using these rules. In the AdaTree, we mainly modified the final hypothesis to get classification rules. In the experiment with WorldView2 image, the result of the method based on AdaTree showed obvious accuracy and efficient improvement compared with the method based on SVM with the kappa coefficient achieving 0.9242

  3. PCA based feature reduction to improve the accuracy of decision tree c4.5 classification

    Science.gov (United States)

    Nasution, M. Z. F.; Sitompul, O. S.; Ramli, M.

    2018-03-01

    Splitting attribute is a major process in Decision Tree C4.5 classification. However, this process does not give a significant impact on the establishment of the decision tree in terms of removing irrelevant features. It is a major problem in decision tree classification process called over-fitting resulting from noisy data and irrelevant features. In turns, over-fitting creates misclassification and data imbalance. Many algorithms have been proposed to overcome misclassification and overfitting on classifications Decision Tree C4.5. Feature reduction is one of important issues in classification model which is intended to remove irrelevant data in order to improve accuracy. The feature reduction framework is used to simplify high dimensional data to low dimensional data with non-correlated attributes. In this research, we proposed a framework for selecting relevant and non-correlated feature subsets. We consider principal component analysis (PCA) for feature reduction to perform non-correlated feature selection and Decision Tree C4.5 algorithm for the classification. From the experiments conducted using available data sets from UCI Cervical cancer data set repository with 858 instances and 36 attributes, we evaluated the performance of our framework based on accuracy, specificity and precision. Experimental results show that our proposed framework is robust to enhance classification accuracy with 90.70% accuracy rates.

  4. Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning

    Energy Technology Data Exchange (ETDEWEB)

    Möller, A. [Research School of Astronomy and Astrophysics, Australian National University, Canberra, ACT 2611 (Australia); Ruhlmann-Kleider, V.; Leloup, C.; Neveu, J.; Palanque-Delabrouille, N.; Rich, J. [Irfu, SPP, CEA Saclay, F-91191 Gif sur Yvette Cedex (France); Carlberg, R. [Department of Astronomy and Astrophysics, University of Toronto, 50 St. George Street, Toronto, ON M5S 3H8 (Canada); Lidman, C. [Australian Astronomical Observatory, North Ryde, NSW 2113 (Australia); Pritchet, C., E-mail: anais.moller@anu.edu.au, E-mail: vanina.ruhlmann-kleider@cea.fr, E-mail: clement.leloup@cea.fr, E-mail: jneveu@lal.in2p3.fr, E-mail: nathalie.palanque-delabrouille@cea.fr, E-mail: james.rich@cea.fr, E-mail: raymond.carlberg@utoronto.ca, E-mail: chris.lidman@aao.gov.au, E-mail: pritchet@uvic.ca [Department of Physics and Astronomy, University of Victoria, P.O. Box 3055, Victoria, BC V8W 3P6 (Canada)

    2016-12-01

    In the era of large astronomical surveys, photometric classification of supernovae (SNe) has become an important research field due to limited spectroscopic resources for candidate follow-up and classification. In this work, we present a method to photometrically classify type Ia supernovae based on machine learning with redshifts that are derived from the SN light-curves. This method is implemented on real data from the SNLS deferred pipeline, a purely photometric pipeline that identifies SNe Ia at high-redshifts (0.2 < z < 1.1). Our method consists of two stages: feature extraction (obtaining the SN redshift from photometry and estimating light-curve shape parameters) and machine learning classification. We study the performance of different algorithms such as Random Forest and Boosted Decision Trees. We evaluate the performance using SN simulations and real data from the first 3 years of the Supernova Legacy Survey (SNLS), which contains large spectroscopically and photometrically classified type Ia samples. Using the Area Under the Curve (AUC) metric, where perfect classification is given by 1, we find that our best-performing classifier (Extreme Gradient Boosting Decision Tree) has an AUC of 0.98.We show that it is possible to obtain a large photometrically selected type Ia SN sample with an estimated contamination of less than 5%. When applied to data from the first three years of SNLS, we obtain 529 events. We investigate the differences between classifying simulated SNe, and real SN survey data. In particular, we find that applying a thorough set of selection cuts to the SN sample is essential for good classification. This work demonstrates for the first time the feasibility of machine learning classification in a high- z SN survey with application to real SN data.

  5. Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning

    International Nuclear Information System (INIS)

    Möller, A.; Ruhlmann-Kleider, V.; Leloup, C.; Neveu, J.; Palanque-Delabrouille, N.; Rich, J.; Carlberg, R.; Lidman, C.; Pritchet, C.

    2016-01-01

    In the era of large astronomical surveys, photometric classification of supernovae (SNe) has become an important research field due to limited spectroscopic resources for candidate follow-up and classification. In this work, we present a method to photometrically classify type Ia supernovae based on machine learning with redshifts that are derived from the SN light-curves. This method is implemented on real data from the SNLS deferred pipeline, a purely photometric pipeline that identifies SNe Ia at high-redshifts (0.2 < z < 1.1). Our method consists of two stages: feature extraction (obtaining the SN redshift from photometry and estimating light-curve shape parameters) and machine learning classification. We study the performance of different algorithms such as Random Forest and Boosted Decision Trees. We evaluate the performance using SN simulations and real data from the first 3 years of the Supernova Legacy Survey (SNLS), which contains large spectroscopically and photometrically classified type Ia samples. Using the Area Under the Curve (AUC) metric, where perfect classification is given by 1, we find that our best-performing classifier (Extreme Gradient Boosting Decision Tree) has an AUC of 0.98.We show that it is possible to obtain a large photometrically selected type Ia SN sample with an estimated contamination of less than 5%. When applied to data from the first three years of SNLS, we obtain 529 events. We investigate the differences between classifying simulated SNe, and real SN survey data. In particular, we find that applying a thorough set of selection cuts to the SN sample is essential for good classification. This work demonstrates for the first time the feasibility of machine learning classification in a high- z SN survey with application to real SN data.

  6. A novel approach to internal crown characterization for coniferous tree species classification

    Science.gov (United States)

    Harikumar, A.; Bovolo, F.; Bruzzone, L.

    2016-10-01

    The knowledge about individual trees in forest is highly beneficial in forest management. High density small foot- print multi-return airborne Light Detection and Ranging (LiDAR) data can provide a very accurate information about the structural properties of individual trees in forests. Every tree species has a unique set of crown structural characteristics that can be used for tree species classification. In this paper, we use both the internal and external crown structural information of a conifer tree crown, derived from a high density small foot-print multi-return LiDAR data acquisition for species classification. Considering the fact that branches are the major building blocks of a conifer tree crown, we obtain the internal crown structural information using a branch level analysis. The structure of each conifer branch is represented using clusters in the LiDAR point cloud. We propose the joint use of the k-means clustering and geometric shape fitting, on the LiDAR data projected onto a novel 3-dimensional space, to identify branch clusters. After mapping the identified clusters back to the original space, six internal geometric features are estimated using a branch-level analysis. The external crown characteristics are modeled by using six least correlated features based on cone fitting and convex hull. Species classification is performed using a sparse Support Vector Machines (sparse SVM) classifier.

  7. Machine Learning Classification of Buildings for Map Generalization

    Directory of Open Access Journals (Sweden)

    Jaeeun Lee

    2017-10-01

    Full Text Available A critical problem in mapping data is the frequent updating of large data sets. To solve this problem, the updating of small-scale data based on large-scale data is very effective. Various map generalization techniques, such as simplification, displacement, typification, elimination, and aggregation, must therefore be applied. In this study, we focused on the elimination and aggregation of the building layer, for which each building in a large scale was classified as “0-eliminated,” “1-retained,” or “2-aggregated.” Machine-learning classification algorithms were then used for classifying the buildings. The data of 1:1000 scale and 1:25,000 scale digital maps obtained from the National Geographic Information Institute were used. We applied to these data various machine-learning classification algorithms, including naive Bayes (NB, decision tree (DT, k-nearest neighbor (k-NN, and support vector machine (SVM. The overall accuracies of each algorithm were satisfactory: DT, 88.96%; k-NN, 88.27%; SVM, 87.57%; and NB, 79.50%. Although elimination is a direct part of the proposed process, generalization operations, such as simplification and aggregation of polygons, must still be performed for buildings classified as retained and aggregated. Thus, these algorithms can be used for building classification and can serve as preparatory steps for building generalization.

  8. Predictive mapping of soil organic carbon in wet cultivated lands using classification-tree based models

    DEFF Research Database (Denmark)

    Kheir, Rania Bou; Greve, Mogens Humlekrog; Bøcher, Peder Klith

    2010-01-01

    the geographic distribution of SOC across Denmark using remote sensing (RS), geographic information systems (GISs) and decision-tree modeling (un-pruned and pruned classification trees). Seventeen parameters, i.e. parent material, soil type, landscape type, elevation, slope gradient, slope aspect, mean curvature...... field measurements in the area of interest (Denmark). A large number of tree-based classification models (588) were developed using (i) all of the parameters, (ii) all Digital Elevation Model (DEM) parameters only, (iii) the primary DEM parameters only, (iv), the remote sensing (RS) indices only, (v......) selected pairs of parameters, (vi) soil type, parent material and landscape type only, and (vii) the parameters having a high impact on SOC distribution in built pruned trees. The best constructed classification tree models (in the number of three) with the lowest misclassification error (ME...

  9. CROWN-LEVEL TREE SPECIES CLASSIFICATION USING INTEGRATED AIRBORNE HYPERSPECTRAL AND LIDAR REMOTE SENSING DATA

    Directory of Open Access Journals (Sweden)

    Z. Wang

    2018-05-01

    Full Text Available Mapping tree species is essential for sustainable planning as well as to improve our understanding of the role of different trees as different ecological service. However, crown-level tree species automatic classification is a challenging task due to the spectral similarity among diversified tree species, fine-scale spatial variation, shadow, and underlying objects within a crown. Advanced remote sensing data such as airborne Light Detection and Ranging (LiDAR and hyperspectral imagery offer a great potential opportunity to derive crown spectral, structure and canopy physiological information at the individual crown scale, which can be useful for mapping tree species. In this paper, an innovative approach was developed for tree species classification at the crown level. The method utilized LiDAR data for individual tree crown delineation and morphological structure extraction, and Compact Airborne Spectrographic Imager (CASI hyperspectral imagery for pure crown-scale spectral extraction. Specifically, four steps were include: 1 A weighted mean filtering method was developed to improve the accuracy of the smoothed Canopy Height Model (CHM derived from LiDAR data; 2 The marker-controlled watershed segmentation algorithm was, therefore, also employed to delineate the tree-level canopy from the CHM image in this study, and then individual tree height and tree crown were calculated according to the delineated crown; 3 Spectral features within 3 × 3 neighborhood regions centered on the treetops detected by the treetop detection algorithm were derived from the spectrally normalized CASI imagery; 4 The shape characteristics related to their crown diameters and heights were established, and different crown-level tree species were classified using the combination of spectral and shape characteristics. Analysis of results suggests that the developed classification strategy in this paper (OA = 85.12 %, Kc = 0.90 performed better than Li

  10. Decision tree approach for classification of remotely sensed satellite ...

    Indian Academy of Sciences (India)

    sensed satellite data using open source support. Richa Sharma .... Decision tree classification techniques have been .... the USGS Earth Resource Observation Systems. (EROS) ... for shallow water, 11% were for sparse and dense built-up ...

  11. Crown-level tree species classification from AISA hyperspectral imagery using an innovative pixel-weighting approach

    Science.gov (United States)

    Liu, Haijian; Wu, Changshan

    2018-06-01

    Crown-level tree species classification is a challenging task due to the spectral similarity among different tree species. Shadow, underlying objects, and other materials within a crown may decrease the purity of extracted crown spectra and further reduce classification accuracy. To address this problem, an innovative pixel-weighting approach was developed for tree species classification at the crown level. The method utilized high density discrete LiDAR data for individual tree delineation and Airborne Imaging Spectrometer for Applications (AISA) hyperspectral imagery for pure crown-scale spectra extraction. Specifically, three steps were included: 1) individual tree identification using LiDAR data, 2) pixel-weighted representative crown spectra calculation using hyperspectral imagery, with which pixel-based illuminated-leaf fractions estimated using a linear spectral mixture analysis (LSMA) were employed as weighted factors, and 3) representative spectra based tree species classification was performed through applying a support vector machine (SVM) approach. Analysis of results suggests that the developed pixel-weighting approach (OA = 82.12%, Kc = 0.74) performed better than treetop-based (OA = 70.86%, Kc = 0.58) and pixel-majority methods (OA = 72.26, Kc = 0.62) in terms of classification accuracy. McNemar tests indicated the differences in accuracy between pixel-weighting and treetop-based approaches as well as that between pixel-weighting and pixel-majority approaches were statistically significant.

  12. Decision tree approach for classification of remotely sensed satellite

    Indian Academy of Sciences (India)

    DTC) algorithm for classification of remotely sensed satellite data (Landsat TM) using open source support. The decision tree is constructed by recursively partitioning the spectral distribution of the training dataset using WEKA, open source ...

  13. Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

    Directory of Open Access Journals (Sweden)

    Ivana Đurđević Babić

    2015-03-01

    Full Text Available Student satisfaction with courses in academic institutions is an important issue and is recognized as a form of support in ensuring effective and quality education, as well as enhancing student course experience. This paper investigates whether there is a connection between student satisfaction with courses and log data on student courses in a virtual learning environment. Furthermore, it explores whether a successful classification model for predicting student satisfaction with course can be developed based on course log data and compares the results obtained from implemented methods. The research was conducted at the Faculty of Education in Osijek and included analysis of log data and course satisfaction on a sample of third and fourth year students. Multilayer Perceptron (MLP with different activation functions and Radial Basis Function (RBF neural networks as well as classification tree models were developed, trained and tested in order to classify students into one of two categories of course satisfaction. Type I and type II errors, and input variable importance were used for model comparison and classification accuracy. The results indicate that a successful classification model using tested methods can be created. The MLP model provides the highest average classification accuracy and the lowest preference in misclassification of students with a low level of course satisfaction, although a t-test for the difference in proportions showed that the difference in performance between the compared models is not statistically significant. Student involvement in forum discussions is recognized as a valuable predictor of student satisfaction with courses in all observed models.

  14. Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines.

    Science.gov (United States)

    Lajnef, Tarek; Chaibi, Sahbi; Ruby, Perrine; Aguera, Pierre-Emmanuel; Eichenlaub, Jean-Baptiste; Samet, Mounir; Kachouri, Abdennaceur; Jerbi, Karim

    2015-07-30

    Sleep staging is a critical step in a range of electrophysiological signal processing pipelines used in clinical routine as well as in sleep research. Although the results currently achievable with automatic sleep staging methods are promising, there is need for improvement, especially given the time-consuming and tedious nature of visual sleep scoring. Here we propose a sleep staging framework that consists of a multi-class support vector machine (SVM) classification based on a decision tree approach. The performance of the method was evaluated using polysomnographic data from 15 subjects (electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) recordings). The decision tree, or dendrogram, was obtained using a hierarchical clustering technique and a wide range of time and frequency-domain features were extracted. Feature selection was carried out using forward sequential selection and classification was evaluated using k-fold cross-validation. The dendrogram-based SVM (DSVM) achieved mean specificity, sensitivity and overall accuracy of 0.92, 0.74 and 0.88 respectively, compared to expert visual scoring. Restricting DSVM classification to data where both experts' scoring was consistent (76.73% of the data) led to a mean specificity, sensitivity and overall accuracy of 0.94, 0.82 and 0.92 respectively. The DSVM framework outperforms classification with more standard multi-class "one-against-all" SVM and linear-discriminant analysis. The promising results of the proposed methodology suggest that it may be a valuable alternative to existing automatic methods and that it could accelerate visual scoring by providing a robust starting hypnogram that can be further fine-tuned by expert inspection. Copyright © 2015 Elsevier B.V. All rights reserved.

  15. Learning features for tissue classification with the classification restricted Boltzmann machine

    DEFF Research Database (Denmark)

    van Tulder, Gijs; de Bruijne, Marleen

    2014-01-01

    Performance of automated tissue classification in medical imaging depends on the choice of descriptive features. In this paper, we show how restricted Boltzmann machines (RBMs) can be used to learn features that are especially suited for texture-based tissue classification. We introduce the convo...... outperform conventional RBM-based feature learning, which is unsupervised and uses only a generative learning objective, as well as often-used filter banks. We show that a mixture of generative and discriminative learning can produce filters that give a higher classification accuracy....

  16. Deep Learning for ECG Classification

    Science.gov (United States)

    Pyakillya, B.; Kazachenko, N.; Mikhailovsky, N.

    2017-10-01

    The importance of ECG classification is very high now due to many current medical applications where this problem can be stated. Currently, there are many machine learning (ML) solutions which can be used for analyzing and classifying ECG data. However, the main disadvantages of these ML results is use of heuristic hand-crafted or engineered features with shallow feature learning architectures. The problem relies in the possibility not to find most appropriate features which will give high classification accuracy in this ECG problem. One of the proposing solution is to use deep learning architectures where first layers of convolutional neurons behave as feature extractors and in the end some fully-connected (FCN) layers are used for making final decision about ECG classes. In this work the deep learning architecture with 1D convolutional layers and FCN layers for ECG classification is presented and some classification results are showed.

  17. Deep learning for image classification

    Science.gov (United States)

    McCoppin, Ryan; Rizki, Mateen

    2014-06-01

    This paper provides an overview of deep learning and introduces the several subfields of deep learning including a specific tutorial of convolutional neural networks. Traditional methods for learning image features are compared to deep learning techniques. In addition, we present our preliminary classification results, our basic implementation of a convolutional restricted Boltzmann machine on the Mixed National Institute of Standards and Technology database (MNIST), and we explain how to use deep learning networks to assist in our development of a robust gender classification system.

  18. Machine learning methods can replace 3D profile method in classification of amyloidogenic hexapeptides

    Directory of Open Access Journals (Sweden)

    Stanislawski Jerzy

    2013-01-01

    Full Text Available Abstract Background Amyloids are proteins capable of forming fibrils. Many of them underlie serious diseases, like Alzheimer disease. The number of amyloid-associated diseases is constantly increasing. Recent studies indicate that amyloidogenic properties can be associated with short segments of aminoacids, which transform the structure when exposed. A few hundreds of such peptides have been experimentally found. Experimental testing of all possible aminoacid combinations is currently not feasible. Instead, they can be predicted by computational methods. 3D profile is a physicochemical-based method that has generated the most numerous dataset - ZipperDB. However, it is computationally very demanding. Here, we show that dataset generation can be accelerated. Two methods to increase the classification efficiency of amyloidogenic candidates are presented and tested: simplified 3D profile generation and machine learning methods. Results We generated a new dataset of hexapeptides, using more economical 3D profile algorithm, which showed very good classification overlap with ZipperDB (93.5%. The new part of our dataset contains 1779 segments, with 204 classified as amyloidogenic. The dataset of 6-residue sequences with their binary classification, based on the energy of the segment, was applied for training machine learning methods. A separate set of sequences from ZipperDB was used as a test set. The most effective methods were Alternating Decision Tree and Multilayer Perceptron. Both methods obtained area under ROC curve of 0.96, accuracy 91%, true positive rate ca. 78%, and true negative rate 95%. A few other machine learning methods also achieved a good performance. The computational time was reduced from 18-20 CPU-hours (full 3D profile to 0.5 CPU-hours (simplified 3D profile to seconds (machine learning. Conclusions We showed that the simplified profile generation method does not introduce an error with regard to the original method, while

  19. Machine learning methods can replace 3D profile method in classification of amyloidogenic hexapeptides.

    Science.gov (United States)

    Stanislawski, Jerzy; Kotulska, Malgorzata; Unold, Olgierd

    2013-01-17

    Amyloids are proteins capable of forming fibrils. Many of them underlie serious diseases, like Alzheimer disease. The number of amyloid-associated diseases is constantly increasing. Recent studies indicate that amyloidogenic properties can be associated with short segments of aminoacids, which transform the structure when exposed. A few hundreds of such peptides have been experimentally found. Experimental testing of all possible aminoacid combinations is currently not feasible. Instead, they can be predicted by computational methods. 3D profile is a physicochemical-based method that has generated the most numerous dataset - ZipperDB. However, it is computationally very demanding. Here, we show that dataset generation can be accelerated. Two methods to increase the classification efficiency of amyloidogenic candidates are presented and tested: simplified 3D profile generation and machine learning methods. We generated a new dataset of hexapeptides, using more economical 3D profile algorithm, which showed very good classification overlap with ZipperDB (93.5%). The new part of our dataset contains 1779 segments, with 204 classified as amyloidogenic. The dataset of 6-residue sequences with their binary classification, based on the energy of the segment, was applied for training machine learning methods. A separate set of sequences from ZipperDB was used as a test set. The most effective methods were Alternating Decision Tree and Multilayer Perceptron. Both methods obtained area under ROC curve of 0.96, accuracy 91%, true positive rate ca. 78%, and true negative rate 95%. A few other machine learning methods also achieved a good performance. The computational time was reduced from 18-20 CPU-hours (full 3D profile) to 0.5 CPU-hours (simplified 3D profile) to seconds (machine learning). We showed that the simplified profile generation method does not introduce an error with regard to the original method, while increasing the computational efficiency. Our new dataset

  20. Extensions and applications of ensemble-of-trees methods in machine learning

    Science.gov (United States)

    Bleich, Justin

    Ensemble-of-trees algorithms have emerged to the forefront of machine learning due to their ability to generate high forecasting accuracy for a wide array of regression and classification problems. Classic ensemble methodologies such as random forests (RF) and stochastic gradient boosting (SGB) rely on algorithmic procedures to generate fits to data. In contrast, more recent ensemble techniques such as Bayesian Additive Regression Trees (BART) and Dynamic Trees (DT) focus on an underlying Bayesian probability model to generate the fits. These new probability model-based approaches show much promise versus their algorithmic counterparts, but also offer substantial room for improvement. The first part of this thesis focuses on methodological advances for ensemble-of-trees techniques with an emphasis on the more recent Bayesian approaches. In particular, we focus on extensions of BART in four distinct ways. First, we develop a more robust implementation of BART for both research and application. We then develop a principled approach to variable selection for BART as well as the ability to naturally incorporate prior information on important covariates into the algorithm. Next, we propose a method for handling missing data that relies on the recursive structure of decision trees and does not require imputation. Last, we relax the assumption of homoskedasticity in the BART model to allow for parametric modeling of heteroskedasticity. The second part of this thesis returns to the classic algorithmic approaches in the context of classification problems with asymmetric costs of forecasting errors. First we consider the performance of RF and SGB more broadly and demonstrate its superiority to logistic regression for applications in criminology with asymmetric costs. Next, we use RF to forecast unplanned hospital readmissions upon patient discharge with asymmetric costs taken into account. Finally, we explore the construction of stable decision trees for forecasts of

  1. Learning classification models with soft-label information.

    Science.gov (United States)

    Nguyen, Quang; Valizadegan, Hamed; Hauskrecht, Milos

    2014-01-01

    Learning of classification models in medicine often relies on data labeled by a human expert. Since labeling of clinical data may be time-consuming, finding ways of alleviating the labeling costs is critical for our ability to automatically learn such models. In this paper we propose a new machine learning approach that is able to learn improved binary classification models more efficiently by refining the binary class information in the training phase with soft labels that reflect how strongly the human expert feels about the original class labels. Two types of methods that can learn improved binary classification models from soft labels are proposed. The first relies on probabilistic/numeric labels, the other on ordinal categorical labels. We study and demonstrate the benefits of these methods for learning an alerting model for heparin induced thrombocytopenia. The experiments are conducted on the data of 377 patient instances labeled by three different human experts. The methods are compared using the area under the receiver operating characteristic curve (AUC) score. Our AUC results show that the new approach is capable of learning classification models more efficiently compared to traditional learning methods. The improvement in AUC is most remarkable when the number of examples we learn from is small. A new classification learning framework that lets us learn from auxiliary soft-label information provided by a human expert is a promising new direction for learning classification models from expert labels, reducing the time and cost needed to label data.

  2. Automated Detection of Connective Tissue by Tissue Counter Analysis and Classification and Regression Trees

    Directory of Open Access Journals (Sweden)

    Josef Smolle

    2001-01-01

    Full Text Available Objective: To evaluate the feasibility of the CART (Classification and Regression Tree procedure for the recognition of microscopic structures in tissue counter analysis. Methods: Digital microscopic images of H&E stained slides of normal human skin and of primary malignant melanoma were overlayed with regularly distributed square measuring masks (elements and grey value, texture and colour features within each mask were recorded. In the learning set, elements were interactively labeled as representing either connective tissue of the reticular dermis, other tissue components or background. Subsequently, CART models were based on these data sets. Results: Implementation of the CART classification rules into the image analysis program showed that in an independent test set 94.1% of elements classified as connective tissue of the reticular dermis were correctly labeled. Automated measurements of the total amount of tissue and of the amount of connective tissue within a slide showed high reproducibility (r=0.97 and r=0.94, respectively; p < 0.001. Conclusions: CART procedure in tissue counter analysis yields simple and reproducible classification rules for tissue elements.

  3. Application of classification-tree methods to identify nitrate sources in ground water

    Science.gov (United States)

    Spruill, T.B.; Showers, W.J.; Howe, S.S.

    2002-01-01

    A study was conducted to determine if nitrate sources in ground water (fertilizer on crops, fertilizer on golf courses, irrigation spray from hog (Sus scrofa) wastes, and leachate from poultry litter and septic systems) could be classified with 80% or greater success. Two statistical classification-tree models were devised from 48 water samples containing nitrate from five source categories. Model I was constructed by evaluating 32 variables and selecting four primary predictor variables (??15N, nitrate to ammonia ratio, sodium to potassium ratio, and zinc) to identify nitrate sources. A ??15N value of nitrate plus potassium 18.2 indicated inorganic or soil organic N. A nitrate to ammonia ratio 575 indicated nitrate from golf courses. A sodium to potassium ratio 3.2 indicated spray or poultry wastes. A value for zinc 2.8 indicated poultry wastes. Model 2 was devised by using all variables except ??15N. This model also included four variables (sodium plus potassium, nitrate to ammonia ratio, calcium to magnesium ratio, and sodium to potassium ratio) to distinguish categories. Both models were able to distinguish all five source categories with better than 80% overall success and with 71 to 100% success in individual categories using the learning samples. Seventeen water samples that were not used in model development were tested using Model 2 for three categories, and all were correctly classified. Classification-tree models show great potential in identifying sources of contamination and variables important in the source-identification process.

  4. Differential Diagnosis of Erythmato-Squamous Diseases Using Classification and Regression Tree.

    Science.gov (United States)

    Maghooli, Keivan; Langarizadeh, Mostafa; Shahmoradi, Leila; Habibi-Koolaee, Mahdi; Jebraeily, Mohamad; Bouraghi, Hamid

    2016-10-01

    Differential diagnosis of Erythmato-Squamous Diseases (ESD) is a major challenge in the field of dermatology. The ESD diseases are placed into six different classes. Data mining is the process for detection of hidden patterns. In the case of ESD, data mining help us to predict the diseases. Different algorithms were developed for this purpose. we aimed to use the Classification and Regression Tree (CART) to predict differential diagnosis of ESD. we used the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology. For this purpose, the dermatology data set from machine learning repository, UCI was obtained. The Clementine 12.0 software from IBM Company was used for modelling. In order to evaluation of the model we calculate the accuracy, sensitivity and specificity of the model. The proposed model had an accuracy of 94.84% (. 24.42) in order to correct prediction of the ESD disease. Results indicated that using of this classifier could be useful. But, it would be strongly recommended that the combination of machine learning methods could be more useful in terms of prediction of ESD.

  5. Data Clustering and Evolving Fuzzy Decision Tree for Data Base Classification Problems

    Science.gov (United States)

    Chang, Pei-Chann; Fan, Chin-Yuan; Wang, Yen-Wen

    Data base classification suffers from two well known difficulties, i.e., the high dimensionality and non-stationary variations within the large historic data. This paper presents a hybrid classification model by integrating a case based reasoning technique, a Fuzzy Decision Tree (FDT), and Genetic Algorithms (GA) to construct a decision-making system for data classification in various data base applications. The model is major based on the idea that the historic data base can be transformed into a smaller case-base together with a group of fuzzy decision rules. As a result, the model can be more accurately respond to the current data under classifying from the inductions by these smaller cases based fuzzy decision trees. Hit rate is applied as a performance measure and the effectiveness of our proposed model is demonstrated by experimentally compared with other approaches on different data base classification applications. The average hit rate of our proposed model is the highest among others.

  6. A classification tree for the prediction of benign versus malignant disease in patients with small renal masses.

    Science.gov (United States)

    Rendon, Ricardo A; Mason, Ross J; Kirkland, Susan; Lawen, Joseph G; Abdolell, Mohamed

    2014-08-01

    To develop a classification tree for the preoperative prediction of benign versus malignant disease in patients with small renal masses. This is a retrospective study including 395 consecutive patients who underwent surgical treatment for a renal mass classification tree to predict the risk of having a benign renal mass preoperatively was developed using recursive partitioning analysis for repeated measures outcomes. Age, sex, volume on preoperative imaging, tumor location (central/peripheral), degree of endophytic component (1%-100%), and tumor axis position were used as potential predictors to develop the model. Forty-five patients (11.4%) were found to have a benign mass postoperatively. A classification tree has been developed which can predict the risk of benign disease with an accuracy of 88.9% (95% CI: 85.3 to 91.8). The significant prognostic factors in the classification tree are tumor volume, degree of endophytic component and symptoms at diagnosis. As an example of its utilization, a renal mass with a volume of classification tree to predict the risk of benign disease in small renal masses has been developed to aid the clinician when deciding on treatment strategies for small renal masses.

  7. Hierarchical classification with a competitive evolutionary neural tree.

    Science.gov (United States)

    Adams, R G.; Butchart, K; Davey, N

    1999-04-01

    A new, dynamic, tree structured network, the Competitive Evolutionary Neural Tree (CENT) is introduced. The network is able to provide a hierarchical classification of unlabelled data sets. The main advantage that the CENT offers over other hierarchical competitive networks is its ability to self determine the number, and structure, of the competitive nodes in the network, without the need for externally set parameters. The network produces stable classificatory structures by halting its growth using locally calculated heuristics. The results of network simulations are presented over a range of data sets, including Anderson's IRIS data set. The CENT network demonstrates its ability to produce a representative hierarchical structure to classify a broad range of data sets.

  8. Building an asynchronous web-based tool for machine learning classification.

    Science.gov (United States)

    Weber, Griffin; Vinterbo, Staal; Ohno-Machado, Lucila

    2002-01-01

    Various unsupervised and supervised learning methods including support vector machines, classification trees, linear discriminant analysis and nearest neighbor classifiers have been used to classify high-throughput gene expression data. Simpler and more widely accepted statistical tools have not yet been used for this purpose, hence proper comparisons between classification methods have not been conducted. We developed free software that implements logistic regression with stepwise variable selection as a quick and simple method for initial exploration of important genetic markers in disease classification. To implement the algorithm and allow our collaborators in remote locations to evaluate and compare its results against those of other methods, we developed a user-friendly asynchronous web-based application with a minimal amount of programming using free, downloadable software tools. With this program, we show that classification using logistic regression can perform as well as other more sophisticated algorithms, and it has the advantages of being easy to interpret and reproduce. By making the tool freely and easily available, we hope to promote the comparison of classification methods. In addition, we believe our web application can be used as a model for other bioinformatics laboratories that need to develop web-based analysis tools in a short amount of time and on a limited budget.

  9. The effect of the fragmentation problem in decision tree learning applied to the search for single top quark production

    International Nuclear Information System (INIS)

    Vilalta, R; Ocegueda-Hernandez, F; Valerio, R; Watts, G

    2010-01-01

    Decision tree learning constitutes a suitable approach to classification due to its ability to partition the variable space into regions of class-uniform events, while providing a structure amenable to interpretation, in contrast to other methods such as neural networks. But an inherent limitation of decision tree learning is the progressive lessening of the statistical support of the final classifier as clusters of single-class events are split on every partition, a problem known as the fragmentation problem. We describe a software system called DTFE, for Decision Tree Fragmentation Evaluator, that measures the degree of fragmentation caused by a decision tree learner on every event cluster. Clusters are found through a decomposition of the data using a technique known as Spectral Clustering. Each cluster is analyzed in terms of the number and type of partitions induced by the decision tree. Our domain of application lies on the search for single top quark production, a challenging problem due to large and similar backgrounds, low energetic signals, and low number of jets. The output of the machine-learning software tool consists of a series of statistics describing the degree of data fragmentation.

  10. Classification of premalignant pancreatic cancer mass-spectrometry data using decision tree ensembles

    Directory of Open Access Journals (Sweden)

    Wong G William

    2008-06-01

    Full Text Available Abstract Background Pancreatic cancer is the fourth leading cause of cancer death in the United States. Consequently, identification of clinically relevant biomarkers for the early detection of this cancer type is urgently needed. In recent years, proteomics profiling techniques combined with various data analysis methods have been successfully used to gain critical insights into processes and mechanisms underlying pathologic conditions, particularly as they relate to cancer. However, the high dimensionality of proteomics data combined with their relatively small sample sizes poses a significant challenge to current data mining methodology where many of the standard methods cannot be applied directly. Here, we propose a novel methodological framework using machine learning method, in which decision tree based classifier ensembles coupled with feature selection methods, is applied to proteomics data generated from premalignant pancreatic cancer. Results This study explores the utility of three different feature selection schemas (Student t test, Wilcoxon rank sum test and genetic algorithm to reduce the high dimensionality of a pancreatic cancer proteomic dataset. Using the top features selected from each method, we compared the prediction performances of a single decision tree algorithm C4.5 with six different decision-tree based classifier ensembles (Random forest, Stacked generalization, Bagging, Adaboost, Logitboost and Multiboost. We show that ensemble classifiers always outperform single decision tree classifier in having greater accuracies and smaller prediction errors when applied to a pancreatic cancer proteomics dataset. Conclusion In our cross validation framework, classifier ensembles generally have better classification accuracies compared to that of a single decision tree when applied to a pancreatic cancer proteomic dataset, thus suggesting its utility in future proteomics data analysis. Additionally, the use of feature selection

  11. I - Multivariate Classification and Machine Learning in HEP

    CERN Multimedia

    CERN. Geneva

    2016-01-01

    Traditional multivariate methods for classification (Stochastic Gradient Boosted Decision Trees and Multi-Layer Perceptrons) are explained in theory and practise using examples from HEP. General aspects of multivariate classification are discussed, in particular different regularisation techniques. Afterwards, data-driven techniques are introduced and compared to MC-based methods.

  12. Real-time classification of humans versus animals using profiling sensors and hidden Markov tree model

    Science.gov (United States)

    Hossen, Jakir; Jacobs, Eddie L.; Chari, Srikant

    2015-07-01

    Linear pyroelectric array sensors have enabled useful classifications of objects such as humans and animals to be performed with relatively low-cost hardware in border and perimeter security applications. Ongoing research has sought to improve the performance of these sensors through signal processing algorithms. In the research presented here, we introduce the use of hidden Markov tree (HMT) models for object recognition in images generated by linear pyroelectric sensors. HMTs are trained to statistically model the wavelet features of individual objects through an expectation-maximization learning process. Human versus animal classification for a test object is made by evaluating its wavelet features against the trained HMTs using the maximum-likelihood criterion. The classification performance of this approach is compared to two other techniques; a texture, shape, and spectral component features (TSSF) based classifier and a speeded-up robust feature (SURF) classifier. The evaluation indicates that among the three techniques, the wavelet-based HMT model works well, is robust, and has improved classification performance compared to a SURF-based algorithm in equivalent computation time. When compared to the TSSF-based classifier, the HMT model has a slightly degraded performance but almost an order of magnitude improvement in computation time enabling real-time implementation.

  13. CLASSIFICATION OF LEARNING MANAGEMENT SYSTEMS

    Directory of Open Access Journals (Sweden)

    Yu. B. Popova

    2016-01-01

    Full Text Available Using of information technologies and, in particular, learning management systems, increases opportunities of teachers and students in reaching their goals in education. Such systems provide learning content, help organize and monitor training, collect progress statistics and take into account the individual characteristics of each user. Currently, there is a huge inventory of both paid and free systems are physically located both on college servers and in the cloud, offering different features sets of different licensing scheme and the cost. This creates the problem of choosing the best system. This problem is partly due to the lack of comprehensive classification of such systems. Analysis of more than 30 of the most common now automated learning management systems has shown that a classification of such systems should be carried out according to certain criteria, under which the same type of system can be considered. As classification features offered by the author are: cost, functionality, modularity, keeping the customer’s requirements, the integration of content, the physical location of a system, adaptability training. Considering the learning management system within these classifications and taking into account the current trends of their development, it is possible to identify the main requirements to them: functionality, reliability, ease of use, low cost, support for SCORM standard or Tin Can API, modularity and adaptability. According to the requirements at the Software Department of FITR BNTU under the guidance of the author since 2009 take place the development, the use and continuous improvement of their own learning management system.

  14. Wall-to-wall tree type classification using airborne lidar data and CIR images

    DEFF Research Database (Denmark)

    Schumacher, Johannes; Nord-Larsen, Thomas

    2014-01-01

    analysed at the individual tree level (object-based). However, due to computational challenges, most object-based studies cover only smaller areas and experience of larger areas is lacking. We present an approach for an object-based, unsupervised classification of trees into broadleaf or conifer using......-based classification of the TST plots showed an overall accuracy of 84% and a kappa coefficient () of 0.61 when using all plots, and 92% and 0.79, respectively, when leaving out plots with larch. NFI plots were assigned to conifer- or broadleaf-dominated or mixed depending on the area covered by the segments...... of the two tree types. In areas where lidar data were collected specifically during leaf-off conditions, 71% of the NFI plots were assigned correctly into the three categories with = 0.53. Using only NFI plots dominated by one type (broadleaf or conifer), 78% were categorized correctly with = 0...

  15. Estimating population extinction thresholds with categorical classification trees for Louisiana black bears.

    Science.gov (United States)

    Laufenberg, Jared S; Clark, Joseph D; Chandler, Richard B

    2018-01-01

    Monitoring vulnerable species is critical for their conservation. Thresholds or tipping points are commonly used to indicate when populations become vulnerable to extinction and to trigger changes in conservation actions. However, quantitative methods to determine such thresholds have not been well explored. The Louisiana black bear (Ursus americanus luteolus) was removed from the list of threatened and endangered species under the U.S. Endangered Species Act in 2016 and our objectives were to determine the most appropriate parameters and thresholds for monitoring and management action. Capture mark recapture (CMR) data from 2006 to 2012 were used to estimate population parameters and variances. We used stochastic population simulations and conditional classification trees to identify demographic rates for monitoring that would be most indicative of heighted extinction risk. We then identified thresholds that would be reliable predictors of population viability. Conditional classification trees indicated that annual apparent survival rates for adult females averaged over 5 years ([Formula: see text]) was the best predictor of population persistence. Specifically, population persistence was estimated to be ≥95% over 100 years when [Formula: see text], suggesting that this statistic can be used as threshold to trigger management intervention. Our evaluation produced monitoring protocols that reliably predicted population persistence and was cost-effective. We conclude that population projections and conditional classification trees can be valuable tools for identifying extinction thresholds used in monitoring programs.

  16. Estimating population extinction thresholds with categorical classification trees for Louisiana black bears.

    Directory of Open Access Journals (Sweden)

    Jared S Laufenberg

    Full Text Available Monitoring vulnerable species is critical for their conservation. Thresholds or tipping points are commonly used to indicate when populations become vulnerable to extinction and to trigger changes in conservation actions. However, quantitative methods to determine such thresholds have not been well explored. The Louisiana black bear (Ursus americanus luteolus was removed from the list of threatened and endangered species under the U.S. Endangered Species Act in 2016 and our objectives were to determine the most appropriate parameters and thresholds for monitoring and management action. Capture mark recapture (CMR data from 2006 to 2012 were used to estimate population parameters and variances. We used stochastic population simulations and conditional classification trees to identify demographic rates for monitoring that would be most indicative of heighted extinction risk. We then identified thresholds that would be reliable predictors of population viability. Conditional classification trees indicated that annual apparent survival rates for adult females averaged over 5 years ([Formula: see text] was the best predictor of population persistence. Specifically, population persistence was estimated to be ≥95% over 100 years when [Formula: see text], suggesting that this statistic can be used as threshold to trigger management intervention. Our evaluation produced monitoring protocols that reliably predicted population persistence and was cost-effective. We conclude that population projections and conditional classification trees can be valuable tools for identifying extinction thresholds used in monitoring programs.

  17. Estimating population extinction thresholds with categorical classification trees for Louisiana black bears

    Science.gov (United States)

    Laufenberg, Jared S.; Clark, Joseph D.; Chandler, Richard B.

    2018-01-01

    Monitoring vulnerable species is critical for their conservation. Thresholds or tipping points are commonly used to indicate when populations become vulnerable to extinction and to trigger changes in conservation actions. However, quantitative methods to determine such thresholds have not been well explored. The Louisiana black bear (Ursus americanus luteolus) was removed from the list of threatened and endangered species under the U.S. Endangered Species Act in 2016 and our objectives were to determine the most appropriate parameters and thresholds for monitoring and management action. Capture mark recapture (CMR) data from 2006 to 2012 were used to estimate population parameters and variances. We used stochastic population simulations and conditional classification trees to identify demographic rates for monitoring that would be most indicative of heighted extinction risk. We then identified thresholds that would be reliable predictors of population viability. Conditional classification trees indicated that annual apparent survival rates for adult females averaged over 5 years () was the best predictor of population persistence. Specifically, population persistence was estimated to be ≥95% over 100 years when , suggesting that this statistic can be used as threshold to trigger management intervention. Our evaluation produced monitoring protocols that reliably predicted population persistence and was cost-effective. We conclude that population projections and conditional classification trees can be valuable tools for identifying extinction thresholds used in monitoring programs.

  18. Joint Feature Selection and Classification for Multilabel Learning.

    Science.gov (United States)

    Huang, Jun; Li, Guorong; Huang, Qingming; Wu, Xindong

    2018-03-01

    Multilabel learning deals with examples having multiple class labels simultaneously. It has been applied to a variety of applications, such as text categorization and image annotation. A large number of algorithms have been proposed for multilabel learning, most of which concentrate on multilabel classification problems and only a few of them are feature selection algorithms. Current multilabel classification models are mainly built on a single data representation composed of all the features which are shared by all the class labels. Since each class label might be decided by some specific features of its own, and the problems of classification and feature selection are often addressed independently, in this paper, we propose a novel method which can perform joint feature selection and classification for multilabel learning, named JFSC. Different from many existing methods, JFSC learns both shared features and label-specific features by considering pairwise label correlations, and builds the multilabel classifier on the learned low-dimensional data representations simultaneously. A comparative study with state-of-the-art approaches manifests a competitive performance of our proposed method both in classification and feature selection for multilabel learning.

  19. Galaxy And Mass Assembly: automatic morphological classification of galaxies using statistical learning

    Science.gov (United States)

    Sreejith, Sreevarsha; Pereverzyev, Sergiy, Jr.; Kelvin, Lee S.; Marleau, Francine R.; Haltmeier, Markus; Ebner, Judith; Bland-Hawthorn, Joss; Driver, Simon P.; Graham, Alister W.; Holwerda, Benne W.; Hopkins, Andrew M.; Liske, Jochen; Loveday, Jon; Moffett, Amanda J.; Pimbblet, Kevin A.; Taylor, Edward N.; Wang, Lingyu; Wright, Angus H.

    2018-03-01

    We apply four statistical learning methods to a sample of 7941 galaxies (z test the feasibility of using automated algorithms to classify galaxies. Using 10 features measured for each galaxy (sizes, colours, shape parameters, and stellar mass), we apply the techniques of Support Vector Machines, Classification Trees, Classification Trees with Random Forest (CTRF) and Neural Networks, and returning True Prediction Ratios (TPRs) of 75.8 per cent, 69.0 per cent, 76.2 per cent, and 76.0 per cent, respectively. Those occasions whereby all four algorithms agree with each other yet disagree with the visual classification (`unanimous disagreement') serves as a potential indicator of human error in classification, occurring in ˜ 9 per cent of ellipticals, ˜ 9 per cent of little blue spheroids, ˜ 14 per cent of early-type spirals, ˜ 21 per cent of intermediate-type spirals, and ˜ 4 per cent of late-type spirals and irregulars. We observe that the choice of parameters rather than that of algorithms is more crucial in determining classification accuracy. Due to its simplicity in formulation and implementation, we recommend the CTRF algorithm for classifying future galaxy data sets. Adopting the CTRF algorithm, the TPRs of the five galaxy types are : E, 70.1 per cent; LBS, 75.6 per cent; S0-Sa, 63.6 per cent; Sab-Scd, 56.4 per cent, and Sd-Irr, 88.9 per cent. Further, we train a binary classifier using this CTRF algorithm that divides galaxies into spheroid-dominated (E, LBS, and S0-Sa) and disc-dominated (Sab-Scd and Sd-Irr), achieving an overall accuracy of 89.8 per cent. This translates into an accuracy of 84.9 per cent for spheroid-dominated systems and 92.5 per cent for disc-dominated systems.

  20. Comparisons of likelihood and machine learning methods of individual classification

    Science.gov (United States)

    Guinand, B.; Topchy, A.; Page, K.S.; Burnham-Curtis, M. K.; Punch, W.F.; Scribner, K.T.

    2002-01-01

    Classification methods used in machine learning (e.g., artificial neural networks, decision trees, and k-nearest neighbor clustering) are rarely used with population genetic data. We compare different nonparametric machine learning techniques with parametric likelihood estimations commonly employed in population genetics for purposes of assigning individuals to their population of origin (“assignment tests”). Classifier accuracy was compared across simulated data sets representing different levels of population differentiation (low and high FST), number of loci surveyed (5 and 10), and allelic diversity (average of three or eight alleles per locus). Empirical data for the lake trout (Salvelinus namaycush) exhibiting levels of population differentiation comparable to those used in simulations were examined to further evaluate and compare classification methods. Classification error rates associated with artificial neural networks and likelihood estimators were lower for simulated data sets compared to k-nearest neighbor and decision tree classifiers over the entire range of parameters considered. Artificial neural networks only marginally outperformed the likelihood method for simulated data (0–2.8% lower error rates). The relative performance of each machine learning classifier improved relative likelihood estimators for empirical data sets, suggesting an ability to “learn” and utilize properties of empirical genotypic arrays intrinsic to each population. Likelihood-based estimation methods provide a more accessible option for reliable assignment of individuals to the population of origin due to the intricacies in development and evaluation of artificial neural networks. In recent years, characterization of highly polymorphic molecular markers such as mini- and microsatellites and development of novel methods of analysis have enabled researchers to extend investigations of ecological and evolutionary processes below the population level to the level of

  1. Machine-learning methods in the classification of water bodies

    Directory of Open Access Journals (Sweden)

    Sołtysiak Marek

    2016-06-01

    Full Text Available Amphibian species have been considered as useful ecological indicators. They are used as indicators of environmental contamination, ecosystem health and habitat quality., Amphibian species are sensitive to changes in the aquatic environment and therefore, may form the basis for the classification of water bodies. Water bodies in which there are a large number of amphibian species are especially valuable even if they are located in urban areas. The automation of the classification process allows for a faster evaluation of the presence of amphibian species in the water bodies. Three machine-learning methods (artificial neural networks, decision trees and the k-nearest neighbours algorithm have been used to classify water bodies in Chorzów – one of 19 cities in the Upper Silesia Agglomeration. In this case, classification is a supervised data mining method consisting of several stages such as building the model, the testing phase and the prediction. Seven natural and anthropogenic features of water bodies (e.g. the type of water body, aquatic plants, the purpose of the water body (destination, position of the water body in relation to any possible buildings, condition of the water body, the degree of littering, the shore type and fishing activities have been taken into account in the classification. The data set used in this study involved information about 71 different water bodies and 9 amphibian species living in them. The results showed that the best average classification accuracy was obtained with the multilayer perceptron neural network.

  2. Unsupervised feature learning for autonomous rock image classification

    Science.gov (United States)

    Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

    2017-09-01

    Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

  3. Classification versus inference learning contrasted with real-world categories.

    Science.gov (United States)

    Jones, Erin L; Ross, Brian H

    2011-07-01

    Categories are learned and used in a variety of ways, but the research focus has been on classification learning. Recent work contrasting classification with inference learning of categories found important later differences in category performance. However, theoretical accounts differ on whether this is due to an inherent difference between the tasks or to the implementation decisions. The inherent-difference explanation argues that inference learners focus on the internal structure of the categories--what each category is like--while classification learners focus on diagnostic information to predict category membership. In two experiments, using real-world categories and controlling for earlier methodological differences, inference learners learned more about what each category was like than did classification learners, as evidenced by higher performance on a novel classification test. These results suggest that there is an inherent difference between learning new categories by classifying an item versus inferring a feature.

  4. In Vivo Pattern Classification of Ingestive Behavior in Ruminants Using FBG Sensors and Machine Learning

    OpenAIRE

    Pegorini, Vinicius; Karam, Leandro Zen; Pitta, Christiano Santos Rocha; Cardoso, Rafael; da Silva, Jean Carlos Cardozo; Kalinowski, Hypolito Jos?; Ribeiro, Richardson; Bertotti, F?bio Luiz; Assmann, Tangriani Simioni

    2015-01-01

    Pattern classification of ingestive behavior in grazing animals has extreme importance in studies related to animal nutrition, growth and health. In this paper, a system to classify chewing patterns of ruminants in in vivo experiments is developed. The proposal is based on data collected by optical fiber Bragg grating sensors (FBG) that are processed by machine learning techniques. The FBG sensors measure the biomechanical strain during jaw movements, and a decision tree is responsible for th...

  5. Active Learning for Text Classification

    OpenAIRE

    Hu, Rong

    2011-01-01

    Text classification approaches are used extensively to solve real-world challenges. The success or failure of text classification systems hangs on the datasets used to train them, without a good dataset it is impossible to build a quality system. This thesis examines the applicability of active learning in text classification for the rapid and economical creation of labelled training data. Four main contributions are made in this thesis. First, we present two novel selection strategies to cho...

  6. Classification decision tree in CT imaging: application to the differential diagnosis of solitary pulmonary nodules

    International Nuclear Information System (INIS)

    Ma Hongxia; Guo Yulin; Wang Qiuping; Qiang Yongqian; Liu Min; Guo Xiaojuan; Guo Youmin; Chen Qihang

    2008-01-01

    Objective: To establish classification and regression tree (CART) for differentiating benign from malignant solitary pulmonary nudules (SPN). Methods: One hundred and sixteen consecutive cases with 116 solitary pulmonary nodules, which finally were pathologically proven 54 malignant nodules and 62 benign nodules, were prospectively registered in this research. Twelve clinical presentations and 22 CT findings were collected as predictors. A classification tree was established to distinguish benign SPNs from malignant ones. In the observer test, two groups (one made of junior radiologists and one of senior radiologists) were independently presented with clinical information and CT images without knowing the pathologic and machine-learning results. Performance of observers and CART were compared by receiver operating characteristic analysis. Results: Receiver operating characteristic analysis showed areas under the curve of CART, senior radiologists and junior radiologists respectively were 0.910±0.029, 0.827±0.038, 0.612±0.052. Difference between areas(DBF) between CART and junior radiologists was 0.297(P<0.01). DBF between CART and senior radiologists was 0.083 (P<0.05). DBF between senior and junior radiologists was 0.214 (P<0.01). CART showed a best diagnostic efficiency, followed by junior radiologists, and then senior radiologists. Conclusion: Our data mining techniques using CART prove a high accuracy in differentiating benign from malignant pulmonary nodules based on clinical variables and CT findings. It will be a potentially useful tool in further application of artificial intelligence in the imaging diagnosis. (authors)

  7. Prediction of Infertility Treatment Outcomes Using Classification Trees

    Directory of Open Access Journals (Sweden)

    Milewska Anna Justyna

    2016-12-01

    Full Text Available Infertility is currently a common problem with causes that are often unexplained, which complicates treatment. In many cases, the use of ART methods provides the only possibility of getting pregnant. Analysis of this type of data is very complex. More and more often, data mining methods or artificial intelligence techniques are appropriate for solving such problems. In this study, classification trees were used for analysis. This resulted in obtaining a group of patients characterized most likely to get pregnant while using in vitro fertilization.

  8. In Vivo Pattern Classification of Ingestive Behavior in Ruminants Using FBG Sensors and Machine Learning

    Directory of Open Access Journals (Sweden)

    Vinicius Pegorini

    2015-11-01

    Full Text Available Pattern classification of ingestive behavior in grazing animals has extreme importance in studies related to animal nutrition, growth and health. In this paper, a system to classify chewing patterns of ruminants in in vivo experiments is developed. The proposal is based on data collected by optical fiber Bragg grating sensors (FBG that are processed by machine learning techniques. The FBG sensors measure the biomechanical strain during jaw movements, and a decision tree is responsible for the classification of the associated chewing pattern. In this study, patterns associated with food intake of dietary supplement, hay and ryegrass were considered. Additionally, two other important events for ingestive behavior were monitored: rumination and idleness. Experimental results show that the proposed approach for pattern classification is capable of differentiating the five patterns involved in the chewing process with an overall accuracy of 94%.

  9. In Vivo Pattern Classification of Ingestive Behavior in Ruminants Using FBG Sensors and Machine Learning.

    Science.gov (United States)

    Pegorini, Vinicius; Karam, Leandro Zen; Pitta, Christiano Santos Rocha; Cardoso, Rafael; da Silva, Jean Carlos Cardozo; Kalinowski, Hypolito José; Ribeiro, Richardson; Bertotti, Fábio Luiz; Assmann, Tangriani Simioni

    2015-11-11

    Pattern classification of ingestive behavior in grazing animals has extreme importance in studies related to animal nutrition, growth and health. In this paper, a system to classify chewing patterns of ruminants in in vivo experiments is developed. The proposal is based on data collected by optical fiber Bragg grating sensors (FBG) that are processed by machine learning techniques. The FBG sensors measure the biomechanical strain during jaw movements, and a decision tree is responsible for the classification of the associated chewing pattern. In this study, patterns associated with food intake of dietary supplement, hay and ryegrass were considered. Additionally, two other important events for ingestive behavior were monitored: rumination and idleness. Experimental results show that the proposed approach for pattern classification is capable of differentiating the five patterns involved in the chewing process with an overall accuracy of 94%.

  10. Iqpc 2015 Track: Tree Separation and Classification in Mobile Mapping LIDAR Data

    Science.gov (United States)

    Gorte, B.; Oude Elberink, S.; Sirmacek, B.; Wang, J.

    2015-08-01

    The European FP7 project IQmulus yearly organizes several processing contests, where submissions are requested for novel algorithms for point cloud and other big geodata processing. This paper describes the set-up and execution of a contest having the purpose to evaluate state-of-the-art algorithms for Mobile Mapping System point clouds, in order to detect and identify (individual) trees. By the nature of MMS these are trees in the vicinity of the road network (rather than in forests). Therefore, part of the challenge is distinguishing between trees and other objects, such as buildings, street furniture, cars etc. Three submitted segmentation and classification algorithms are thus evaluated.

  11. A new approach to enhance the performance of decision tree for classifying gene expression data.

    Science.gov (United States)

    Hassan, Md; Kotagiri, Ramamohanarao

    2013-12-20

    Gene expression data classification is a challenging task due to the large dimensionality and very small number of samples. Decision tree is one of the popular machine learning approaches to address such classification problems. However, the existing decision tree algorithms use a single gene feature at each node to split the data into its child nodes and hence might suffer from poor performance specially when classifying gene expression dataset. By using a new decision tree algorithm where, each node of the tree consists of more than one gene, we enhance the classification performance of traditional decision tree classifiers. Our method selects suitable genes that are combined using a linear function to form a derived composite feature. To determine the structure of the tree we use the area under the Receiver Operating Characteristics curve (AUC). Experimental analysis demonstrates higher classification accuracy using the new decision tree compared to the other existing decision trees in literature. We experimentally compare the effect of our scheme against other well known decision tree techniques. Experiments show that our algorithm can substantially boost the classification performance of the decision tree.

  12. Observation versus classification in supervised category learning.

    Science.gov (United States)

    Levering, Kimery R; Kurtz, Kenneth J

    2015-02-01

    The traditional supervised classification paradigm encourages learners to acquire only the knowledge needed to predict category membership (a discriminative approach). An alternative that aligns with important aspects of real-world concept formation is learning with a broader focus to acquire knowledge of the internal structure of each category (a generative approach). Our work addresses the impact of a particular component of the traditional classification task: the guess-and-correct cycle. We compare classification learning to a supervised observational learning task in which learners are shown labeled examples but make no classification response. The goals of this work sit at two levels: (1) testing for differences in the nature of the category representations that arise from two basic learning modes; and (2) evaluating the generative/discriminative continuum as a theoretical tool for understand learning modes and their outcomes. Specifically, we view the guess-and-correct cycle as consistent with a more discriminative approach and therefore expected it to lead to narrower category knowledge. Across two experiments, the observational mode led to greater sensitivity to distributional properties of features and correlations between features. We conclude that a relatively subtle procedural difference in supervised category learning substantially impacts what learners come to know about the categories. The results demonstrate the value of the generative/discriminative continuum as a tool for advancing the psychology of category learning and also provide a valuable constraint for formal models and associated theories.

  13. Tree species classification using within crown localization of waveform LiDAR attributes

    Science.gov (United States)

    Blomley, Rosmarie; Hovi, Aarne; Weinmann, Martin; Hinz, Stefan; Korpela, Ilkka; Jutzi, Boris

    2017-11-01

    Since forest planning is increasingly taking an ecological, diversity-oriented perspective into account, remote sensing technologies are becoming ever more important in assessing existing resources with reduced manual effort. While the light detection and ranging (LiDAR) technology provides a good basis for predictions of tree height and biomass, tree species identification based on this type of data is particularly challenging in structurally heterogeneous forests. In this paper, we analyse existing approaches with respect to the geometrical scale of feature extraction (whole tree, within crown partitions or within laser footprint) and conclude that currently features are always extracted separately from the different scales. Since multi-scale approaches however have proven successful in other applications, we aim to utilize the within-tree-crown distribution of within-footprint signal characteristics as additional features. To do so, a spin image algorithm, originally devised for the extraction of 3D surface features in object recognition, is adapted. This algorithm relies on spinning an image plane around a defined axis, e.g. the tree stem, collecting the number of LiDAR returns or mean values of returns attributes per pixel as respective values. Based on this representation, spin image features are extracted that comprise only those components of highest variability among a given set of library trees. The relative performance and the combined improvement of these spin image features with respect to non-spatial statistical metrics of the waveform (WF) attributes are evaluated for the tree species classification of Scots pine (Pinus sylvestris L.), Norway spruce (Picea abies (L.) Karst.) and Silver/Downy birch (Betula pendula Roth/Betula pubescens Ehrh.) in a boreal forest environment. This evaluation is performed for two WF LiDAR datasets that differ in footprint size, pulse density at ground, laser wavelength and pulse width. Furthermore, we evaluate the

  14. Prospective identification of adolescent suicide ideation using classification tree analysis: Models for community-based screening.

    Science.gov (United States)

    Hill, Ryan M; Oosterhoff, Benjamin; Kaplow, Julie B

    2017-07-01

    Although a large number of risk markers for suicide ideation have been identified, little guidance has been provided to prospectively identify adolescents at risk for suicide ideation within community settings. The current study addressed this gap in the literature by utilizing classification tree analysis (CTA) to provide a decision-making model for screening adolescents at risk for suicide ideation. Participants were N = 4,799 youth (Mage = 16.15 years, SD = 1.63) who completed both Waves 1 and 2 of the National Longitudinal Study of Adolescent to Adult Health. CTA was used to generate a series of decision rules for identifying adolescents at risk for reporting suicide ideation at Wave 2. Findings revealed 3 distinct solutions with varying sensitivity and specificity for identifying adolescents who reported suicide ideation. Sensitivity of the classification trees ranged from 44.6% to 77.6%. The tree with greatest specificity and lowest sensitivity was based on a history of suicide ideation. The tree with moderate sensitivity and high specificity was based on depressive symptoms, suicide attempts or suicide among family and friends, and social support. The most sensitive but least specific tree utilized these factors and gender, ethnicity, hours of sleep, school-related factors, and future orientation. These classification trees offer community organizations options for instituting large-scale screenings for suicide ideation risk depending on the available resources and modality of services to be provided. This study provides a theoretically and empirically driven model for prospectively identifying adolescents at risk for suicide ideation and has implications for preventive interventions among at-risk youth. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  15. Classification and Compression of Multi-Resolution Vectors: A Tree Structured Vector Quantizer Approach

    Science.gov (United States)

    2002-01-01

    their expression profile and for classification of cells into tumerous and non- tumerous classes. Then we will present a parallel tree method for... cancerous cells. We will use the same dataset and use tree structured classifiers with multi-resolution analysis for classifying cancerous from non- cancerous ...cells. We have the expressions of 4096 genes from 98 different cell types. Of these 98, 72 are cancerous while 26 are non- cancerous . We are interested

  16. Classification and Optimization of Decision Trees for Inconsistent Decision Tables Represented as MVD Tables

    KAUST Repository

    Azad, Mohammad

    2015-10-11

    Decision tree is a widely used technique to discover patterns from consistent data set. But if the data set is inconsistent, where there are groups of examples (objects) with equal values of conditional attributes but different decisions (values of the decision attribute), then to discover the essential patterns or knowledge from the data set is challenging. We consider three approaches (generalized, most common and many-valued decision) to handle such inconsistency. We created different greedy algorithms using various types of impurity and uncertainty measures to construct decision trees. We compared the three approaches based on the decision tree properties of the depth, average depth and number of nodes. Based on the result of the comparison, we choose to work with the many-valued decision approach. Now to determine which greedy algorithms are efficient, we compared them based on the optimization and classification results. It was found that some greedy algorithms Mult\\\\_ws\\\\_entSort, and Mult\\\\_ws\\\\_entML are good for both optimization and classification.

  17. Classification and Optimization of Decision Trees for Inconsistent Decision Tables Represented as MVD Tables

    KAUST Repository

    Azad, Mohammad; Moshkov, Mikhail

    2015-01-01

    Decision tree is a widely used technique to discover patterns from consistent data set. But if the data set is inconsistent, where there are groups of examples (objects) with equal values of conditional attributes but different decisions (values of the decision attribute), then to discover the essential patterns or knowledge from the data set is challenging. We consider three approaches (generalized, most common and many-valued decision) to handle such inconsistency. We created different greedy algorithms using various types of impurity and uncertainty measures to construct decision trees. We compared the three approaches based on the decision tree properties of the depth, average depth and number of nodes. Based on the result of the comparison, we choose to work with the many-valued decision approach. Now to determine which greedy algorithms are efficient, we compared them based on the optimization and classification results. It was found that some greedy algorithms Mult\\_ws\\_entSort, and Mult\\_ws\\_entML are good for both optimization and classification.

  18. Deep learning for tumor classification in imaging mass spectrometry.

    Science.gov (United States)

    Behrmann, Jens; Etmann, Christian; Boskamp, Tobias; Casadonte, Rita; Kriegsmann, Jörg; Maaß, Peter

    2018-04-01

    Tumor classification using imaging mass spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Since mass spectra exhibit certain structural similarities to image data, deep learning may offer a promising strategy for classification of IMS data as it has been successfully applied to image classification. Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two algorithmically challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods is shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered tasks. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks. https://gitlab.informatik.uni-bremen.de/digipath/Deep_Learning_for_Tumor_Classification_in_IMS. jbehrmann@uni-bremen.de or christianetmann@uni-bremen.de. Supplementary data are available at Bioinformatics online.

  19. Learning Apache Mahout classification

    CERN Document Server

    Gupta, Ashish

    2015-01-01

    If you are a data scientist who has some experience with the Hadoop ecosystem and machine learning methods and want to try out classification on large datasets using Mahout, this book is ideal for you. Knowledge of Java is essential.

  20. A SEMI-AUTOMATIC RULE SET BUILDING METHOD FOR URBAN LAND COVER CLASSIFICATION BASED ON MACHINE LEARNING AND HUMAN KNOWLEDGE

    Directory of Open Access Journals (Sweden)

    H. Y. Gu

    2017-09-01

    Full Text Available Classification rule set is important for Land Cover classification, which refers to features and decision rules. The selection of features and decision are based on an iterative trial-and-error approach that is often utilized in GEOBIA, however, it is time-consuming and has a poor versatility. This study has put forward a rule set building method for Land cover classification based on human knowledge and machine learning. The use of machine learning is to build rule sets effectively which will overcome the iterative trial-and-error approach. The use of human knowledge is to solve the shortcomings of existing machine learning method on insufficient usage of prior knowledge, and improve the versatility of rule sets. A two-step workflow has been introduced, firstly, an initial rule is built based on Random Forest and CART decision tree. Secondly, the initial rule is analyzed and validated based on human knowledge, where we use statistical confidence interval to determine its threshold. The test site is located in Potsdam City. We utilised the TOP, DSM and ground truth data. The results show that the method could determine rule set for Land Cover classification semi-automatically, and there are static features for different land cover classes.

  1. Hierarchical Learning of Tree Classifiers for Large-Scale Plant Species Identification.

    Science.gov (United States)

    Fan, Jianping; Zhou, Ning; Peng, Jinye; Gao, Ling

    2015-11-01

    In this paper, a hierarchical multi-task structural learning algorithm is developed to support large-scale plant species identification, where a visual tree is constructed for organizing large numbers of plant species in a coarse-to-fine fashion and determining the inter-related learning tasks automatically. For a given parent node on the visual tree, it contains a set of sibling coarse-grained categories of plant species or sibling fine-grained plant species, and a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly for enhancing their discrimination power. The inter-level relationship constraint, e.g., a plant image must first be assigned to a parent node (high-level non-leaf node) correctly if it can further be assigned to the most relevant child node (low-level non-leaf node or leaf node) on the visual tree, is formally defined and leveraged to learn more discriminative tree classifiers over the visual tree. Our experimental results have demonstrated the effectiveness of our hierarchical multi-task structural learning algorithm on training more discriminative tree classifiers for large-scale plant species identification.

  2. Comparative analysis of tree classification models for detecting fusarium oxysporum f. sp cubense (TR4) based on multi soil sensor parameters

    Science.gov (United States)

    Estuar, Maria Regina Justina; Victorino, John Noel; Coronel, Andrei; Co, Jerelyn; Tiausas, Francis; Señires, Chiara Veronica

    2017-09-01

    Use of wireless sensor networks and smartphone integration design to monitor environmental parameters surrounding plantations is made possible because of readily available and affordable sensors. Providing low cost monitoring devices would be beneficial, especially to small farm owners, in a developing country like the Philippines, where agriculture covers a significant amount of the labor market. This study discusses the integration of wireless soil sensor devices and smartphones to create an application that will use multidimensional analysis to detect the presence or absence of plant disease. Specifically, soil sensors are designed to collect soil quality parameters in a sink node from which the smartphone collects data from via Bluetooth. Given these, there is a need to develop a classification model on the mobile phone that will report infection status of a soil. Though tree classification is the most appropriate approach for continuous parameter-based datasets, there is a need to determine whether tree models will result to coherent results or not. Soil sensor data that resides on the phone is modeled using several variations of decision tree, namely: decision tree (DT), best-fit (BF) decision tree, functional tree (FT), Naive Bayes (NB) decision tree, J48, J48graft and LAD tree, where decision tree approaches the problem by considering all sensor nodes as one. Results show that there are significant differences among soil sensor parameters indicating that there are variances in scores between the infected and uninfected sites. Furthermore, analysis of variance in accuracy, recall, precision and F1 measure scores from tree classification models homogeneity among NBTree, J48graft and J48 tree classification models.

  3. DeepSAT: A Deep Learning Approach to Tree-cover Delineation in 1-m NAIP Imagery for the Continental United States

    Science.gov (United States)

    Ganguly, S.; Basu, S.; Nemani, R. R.; Mukhopadhyay, S.; Michaelis, A.; Votava, P.

    2016-12-01

    High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with 60 million pixels) and has a total size of 65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to 8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the

  4. DeepSAT: A Deep Learning Approach to Tree-Cover Delineation in 1-m NAIP Imagery for the Continental United States

    Science.gov (United States)

    Ganguly, Sangram; Basu, Saikat; Nemani, Ramakrishna R.; Mukhopadhyay, Supratik; Michaelis, Andrew; Votava, Petr

    2016-01-01

    High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with 60 million pixels) and has a total size of 65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to 8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the

  5. Classification tree for the assessment of sedentary lifestyle among hypertensive.

    Science.gov (United States)

    Castelo Guedes Martins, Larissa; Venícios de Oliveira Lopes, Marcos; Gomes Guedes, Nirla; Paixão de Menezes, Angélica; de Oliveira Farias, Odaleia; Alves Dos Santos, Naftale

    2016-04-01

    To develop a classification tree of clinical indicators for the correct prediction of the nursing diagnosis "Sedentary lifestyle" (SL) in people with high blood pressure (HTN). A cross-sectional study conducted in an outpatient care center specializing in high blood pressure and Mellitus diabetes located in northeastern Brazil. The sample consisted of 285 people between 19 and 59 years old diagnosed with high blood pressure and was applied an interview and physical examination, obtaining socio-demographic information, related factors and signs and symptoms that made the defining characteristics for the diagnosis under study. The tree was generated using the CHAID algorithm (Chi-square Automatic Interaction Detection). The construction of the decision tree allowed establishing the interactions between clinical indicators that facilitate a probabilistic analysis of multiple situations allowing quantify the probability of an individual presenting a sedentary lifestyle. The tree included the clinical indicator Choose daily routine without exercise as the first node. People with this indicator showed a probability of 0.88 of presenting the SL. The second node was composed of the indicator Does not perform physical activity during leisure, with 0.99 probability of presenting the SL with these two indicators. The predictive capacity of the tree was established at 69.5%. Decision trees help nurses who care HTN people in decision-making in assessing the characteristics that increase the probability of SL nursing diagnosis, optimizing the time for diagnostic inference.

  6. Classification tree for the assessment of sedentary lifestyle among hypertensive

    Directory of Open Access Journals (Sweden)

    Larissa Castelo Guedes Martins

    Full Text Available Objective.To develop a classification tree of clinical indicators for the correct prediction of the nursing diagnosis "Sedentary lifestyle" (SL in people with high blood pressure (HTN. Methods. A cross-sectional study conducted in an outpatient care center specializing in high blood pressure and Mellitus diabetes located in northeastern Brazil. The sample consisted of 285 people between 19 and 59 years old diagnosed with high blood pressure and was applied an interview and physical examination, obtaining socio-demographic information, related factors and signs and symptoms that made the defining characteristics for the diagnosis under study. The tree was generated using the CHAID algorithm (Chi-square Automatic Interaction Detection. Results. The construction of the decision tree allowed establishing the interactions between clinical indicators that facilitate a probabilistic analysis of multiple situations allowing quantify the probability of an individual presenting a sedentary lifestyle. The tree included the clinical indicator Choose daily routine without exercise as the first node. People with this indicator showed a probability of 0.88 of presenting the SL. The second node was composed of the indicator Does not perform physical activity during leisure, with 0.99 probability of presenting the SL with these two indicators. The predictive capacity of the tree was established at 69.5%. Conclusion. Decision trees help nurses who care HTN people in decision-making in assessing the characteristics that increase the probability of SL nursing diagnosis, optimizing the time for diagnostic inference.

  7. Active Learning of Classification Models with Likert-Scale Feedback.

    Science.gov (United States)

    Xue, Yanbing; Hauskrecht, Milos

    2017-01-01

    Annotation of classification data by humans can be a time-consuming and tedious process. Finding ways of reducing the annotation effort is critical for building the classification models in practice and for applying them to a variety of classification tasks. In this paper, we develop a new active learning framework that combines two strategies to reduce the annotation effort. First, it relies on label uncertainty information obtained from the human in terms of the Likert-scale feedback. Second, it uses active learning to annotate examples with the greatest expected change. We propose a Bayesian approach to calculate the expectation and an incremental SVM solver to reduce the time complexity of the solvers. We show the combination of our active learning strategy and the Likert-scale feedback can learn classification models more rapidly and with a smaller number of labeled instances than methods that rely on either Likert-scale labels or active learning alone.

  8. A fuzzy decision tree method for fault classification in the steam generator of a pressurized water reactor

    International Nuclear Information System (INIS)

    Zio, Enrico; Baraldi, Piero; Popescu, Irina Crenguta

    2009-01-01

    This paper extends a method previously introduced by the authors for building a transparent fault classification algorithm by combining the fuzzy clustering, fuzzy logic and decision trees techniques. The baseline method transforms an opaque, fuzzy clustering-based classification model into a fuzzy logic inference model based on linguistic rules which can be represented by a decision tree formalism. The classification model thereby obtained is transparent in that it allows direct interpretation and inspection of the model. An extension in the procedure for the development of the fuzzy logic inference model is introduced to allow the treatment of more complicated cases, e.g. splitted and overlapping clusters. The corresponding computational tool developed relies on a number of parameters which can be tuned by the user to optimally compromise the level of transparency of the classification process and its efficiency. A numerical application is presented with regards to the fault classification in the Steam Generator of a Pressurized Water Reactor.

  9. Document Classification Using Distributed Machine Learning

    OpenAIRE

    Aydin, Galip; Hallac, Ibrahim Riza

    2018-01-01

    In this paper, we investigate the performance and success rates of Na\\"ive Bayes Classification Algorithm for automatic classification of Turkish news into predetermined categories like economy, life, health etc. We use Apache Big Data technologies such as Hadoop, HDFS, Spark and Mahout, and apply these distributed technologies to Machine Learning.

  10. Polarimetric SAR image classification based on discriminative dictionary learning model

    Science.gov (United States)

    Sang, Cheng Wei; Sun, Hong

    2018-03-01

    Polarimetric SAR (PolSAR) image classification is one of the important applications of PolSAR remote sensing. It is a difficult high-dimension nonlinear mapping problem, the sparse representations based on learning overcomplete dictionary have shown great potential to solve such problem. The overcomplete dictionary plays an important role in PolSAR image classification, however for PolSAR image complex scenes, features shared by different classes will weaken the discrimination of learned dictionary, so as to degrade classification performance. In this paper, we propose a novel overcomplete dictionary learning model to enhance the discrimination of dictionary. The learned overcomplete dictionary by the proposed model is more discriminative and very suitable for PolSAR classification.

  11. Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty

    Energy Technology Data Exchange (ETDEWEB)

    Stocki, Trevor J., E-mail: trevor_stocki@hc-sc.gc.c [Radiation Protection Bureau, 775 Brookfield Road, A.L. 6302D1, Ottawa, ON, K1A 1C1 (Canada); Li, Guichong; Japkowicz, Nathalie [School of Information Technology and Engineering, University of Ottawa, 800 King Edward Avenue, Ottawa, ON, K1N 6N5 (Canada); Ungar, R. Kurt [Radiation Protection Bureau, 775 Brookfield Road, A.L. 6302D1, Ottawa, ON, K1A 1C1 (Canada)

    2010-01-15

    A method of weapon detection for the Comprehensive nuclear-Test-Ban-Treaty (CTBT) consists of monitoring the amount of radioxenon in the atmosphere by measuring and sampling the activity concentration of {sup 131m}Xe, {sup 133}Xe, {sup 133m}Xe, and {sup 135}Xe by radionuclide monitoring. Several explosion samples were simulated based on real data since the measured data of this type is quite rare. These data sets consisted of different circumstances of a nuclear explosion, and are used as training data sets to establish an effective classification model employing state-of-the-art technologies in machine learning. A study was conducted involving classic induction algorithms in machine learning including Naive Bayes, Neural Networks, Decision Trees, k-Nearest Neighbors, and Support Vector Machines, that revealed that they can successfully be used in this practical application. In particular, our studies show that many induction algorithms in machine learning outperform a simple linear discriminator when a signal is found in a high radioxenon background environment.

  12. Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty

    International Nuclear Information System (INIS)

    Stocki, Trevor J.; Li, Guichong; Japkowicz, Nathalie; Ungar, R. Kurt

    2010-01-01

    A method of weapon detection for the Comprehensive nuclear-Test-Ban-Treaty (CTBT) consists of monitoring the amount of radioxenon in the atmosphere by measuring and sampling the activity concentration of 131m Xe, 133 Xe, 133m Xe, and 135 Xe by radionuclide monitoring. Several explosion samples were simulated based on real data since the measured data of this type is quite rare. These data sets consisted of different circumstances of a nuclear explosion, and are used as training data sets to establish an effective classification model employing state-of-the-art technologies in machine learning. A study was conducted involving classic induction algorithms in machine learning including Naive Bayes, Neural Networks, Decision Trees, k-Nearest Neighbors, and Support Vector Machines, that revealed that they can successfully be used in this practical application. In particular, our studies show that many induction algorithms in machine learning outperform a simple linear discriminator when a signal is found in a high radioxenon background environment.

  13. Improving medical diagnosis reliability using Boosted C5.0 decision tree empowered by Particle Swarm Optimization.

    Science.gov (United States)

    Pashaei, Elnaz; Ozen, Mustafa; Aydin, Nizamettin

    2015-08-01

    Improving accuracy of supervised classification algorithms in biomedical applications is one of active area of research. In this study, we improve the performance of Particle Swarm Optimization (PSO) combined with C4.5 decision tree (PSO+C4.5) classifier by applying Boosted C5.0 decision tree as the fitness function. To evaluate the effectiveness of our proposed method, it is implemented on 1 microarray dataset and 5 different medical data sets obtained from UCI machine learning databases. Moreover, the results of PSO + Boosted C5.0 implementation are compared to eight well-known benchmark classification methods (PSO+C4.5, support vector machine under the kernel of Radial Basis Function, Classification And Regression Tree (CART), C4.5 decision tree, C5.0 decision tree, Boosted C5.0 decision tree, Naive Bayes and Weighted K-Nearest neighbor). Repeated five-fold cross-validation method was used to justify the performance of classifiers. Experimental results show that our proposed method not only improve the performance of PSO+C4.5 but also obtains higher classification accuracy compared to the other classification methods.

  14. Deep learning for EEG-Based preference classification

    Science.gov (United States)

    Teo, Jason; Hou, Chew Lin; Mountstephens, James

    2017-10-01

    Electroencephalogram (EEG)-based emotion classification is rapidly becoming one of the most intensely studied areas of brain-computer interfacing (BCI). The ability to passively identify yet accurately correlate brainwaves with our immediate emotions opens up truly meaningful and previously unattainable human-computer interactions such as in forensic neuroscience, rehabilitative medicine, affective entertainment and neuro-marketing. One particularly useful yet rarely explored areas of EEG-based emotion classification is preference recognition [1], which is simply the detection of like versus dislike. Within the limited investigations into preference classification, all reported studies were based on musically-induced stimuli except for a single study which used 2D images. The main objective of this study is to apply deep learning, which has been shown to produce state-of-the-art results in diverse hard problems such as in computer vision, natural language processing and audio recognition, to 3D object preference classification over a larger group of test subjects. A cohort of 16 users was shown 60 bracelet-like objects as rotating visual stimuli on a computer display while their preferences and EEGs were recorded. After training a variety of machine learning approaches which included deep neural networks, we then attempted to classify the users' preferences for the 3D visual stimuli based on their EEGs. Here, we show that that deep learning outperforms a variety of other machine learning classifiers for this EEG-based preference classification task particularly in a highly challenging dataset with large inter- and intra-subject variability.

  15. Classification tree for the assessment of sedentary lifestyle among hypertensive

    OpenAIRE

    Castelo Guedes Martins, Larissa; Venícios de Oliveira Lopes, Marcos; Gomes Guedes, Nirla; Paixão de Menezes, Angélica; de Oliveira Farias, Odaleia; Alves dos Santos, Naftale

    2016-01-01

    Objective.To develop a classification tree of clinical indicators for the correct prediction of the nursing diagnosis "Sedentary lifestyle" (SL) in people with high blood pressure (HTN). Methods. A cross-sectional study conducted in an outpatient care center specializing in high blood pressure and Mellitus diabetes located in northeastern Brazil. The sample consisted of 285 people between 19 and 59 years old diagnosed with high blood pressure and was applied an interview and physical examinat...

  16. Group-Based Active Learning of Classification Models.

    Science.gov (United States)

    Luo, Zhipeng; Hauskrecht, Milos

    2017-05-01

    Learning of classification models from real-world data often requires additional human expert effort to annotate the data. However, this process can be rather costly and finding ways of reducing the human annotation effort is critical for this task. The objective of this paper is to develop and study new ways of providing human feedback for efficient learning of classification models by labeling groups of examples. Briefly, unlike traditional active learning methods that seek feedback on individual examples, we develop a new group-based active learning framework that solicits label information on groups of multiple examples. In order to describe groups in a user-friendly way, conjunctive patterns are used to compactly represent groups. Our empirical study on 12 UCI data sets demonstrates the advantages and superiority of our approach over both classic instance-based active learning work, as well as existing group-based active-learning methods.

  17. A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series.

    Science.gov (United States)

    Chambon, Stanislas; Galtier, Mathieu N; Arnal, Pierrick J; Wainrib, Gilles; Gramfort, Alexandre

    2018-04-01

    Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30 s of the signal of a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEGs), electrooculograms (EOGs), electrocardiograms, and electromyograms (EMGs). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data. For each modality, the first layer learns linear spatial filters that exploit the array of sensors to increase the signal-to-noise ratio, and the last layer feeds the learnt representation to a softmax classifier. Our model is compared to alternative automatic approaches based on convolutional networks or decisions trees. Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance. Our study reveals a number of insights on the spatiotemporal distribution of the signal of interest: a good tradeoff for optimal classification performance measured with balanced accuracy is to use 6 EEG with 2 EOG (left and right) and 3 EMG chin channels. Also exploiting 1 min of data before and after each data segment offers the strongest improvement when a limited number of channels are available. As sleep experts, our system exploits the multivariate and multimodal nature of PSG signals in order to deliver the state-of-the-art classification performance with a small computational cost.

  18. Representation learning with deep extreme learning machines for efficient image set classification

    KAUST Repository

    Uzair, Muhammad

    2016-12-09

    Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.

  19. Representation learning with deep extreme learning machines for efficient image set classification

    KAUST Repository

    Uzair, Muhammad; Shafait, Faisal; Ghanem, Bernard; Mian, Ajmal

    2016-01-01

    Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.

  20. Metabolite identification through multiple kernel learning on fragmentation trees.

    Science.gov (United States)

    Shen, Huibin; Dührkop, Kai; Böcker, Sebastian; Rousu, Juho

    2014-06-15

    Metabolite identification from tandem mass spectrometric data is a key task in metabolomics. Various computational methods have been proposed for the identification of metabolites from tandem mass spectra. Fragmentation tree methods explore the space of possible ways in which the metabolite can fragment, and base the metabolite identification on scoring of these fragmentation trees. Machine learning methods have been used to map mass spectra to molecular fingerprints; predicted fingerprints, in turn, can be used to score candidate molecular structures. Here, we combine fragmentation tree computations with kernel-based machine learning to predict molecular fingerprints and identify molecular structures. We introduce a family of kernels capturing the similarity of fragmentation trees, and combine these kernels using recently proposed multiple kernel learning approaches. Experiments on two large reference datasets show that the new methods significantly improve molecular fingerprint prediction accuracy. These improvements result in better metabolite identification, doubling the number of metabolites ranked at the top position of the candidates list. © The Author 2014. Published by Oxford University Press.

  1. Transfer Learning beyond Text Classification

    Science.gov (United States)

    Yang, Qiang

    Transfer learning is a new machine learning and data mining framework that allows the training and test data to come from different distributions or feature spaces. We can find many novel applications of machine learning and data mining where transfer learning is necessary. While much has been done in transfer learning in text classification and reinforcement learning, there has been a lack of documented success stories of novel applications of transfer learning in other areas. In this invited article, I will argue that transfer learning is in fact quite ubiquitous in many real world applications. In this article, I will illustrate this point through an overview of a broad spectrum of applications of transfer learning that range from collaborative filtering to sensor based location estimation and logical action model learning for AI planning. I will also discuss some potential future directions of transfer learning.

  2. A Weighted Block Dictionary Learning Algorithm for Classification

    OpenAIRE

    Shi, Zhongrong

    2016-01-01

    Discriminative dictionary learning, playing a critical role in sparse representation based classification, has led to state-of-the-art classification results. Among the existing discriminative dictionary learning methods, two different approaches, shared dictionary and class-specific dictionary, which associate each dictionary atom to all classes or a single class, have been studied. The shared dictionary is a compact method but with lack of discriminative information; the class-specific dict...

  3. Multivariate decision tree designing for the classification of multi-jet topologies in e sup + e sup - collisions

    CERN Document Server

    Mjahed, M

    2002-01-01

    The binary decision tree method is used to separate between several multi-jet topologies in e sup + e sup - collisions. Instead of the univariate process usually taken, a new design procedure for constructing multivariate decision trees is proposed. The segmentation is obtained by considering some features functions, where linear and non-linear discriminant functions and a minimal distance method are used. The classification focuses on ALEPH simulated events, with multi-jet topologies. Compared to a standard univariate tree, the multivariate decision trees offer significantly better performance.

  4. Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments

    Science.gov (United States)

    Han, Wenjing; Coutinho, Eduardo; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

    2016-01-01

    Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances. PMID:27627768

  5. Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments.

    Science.gov (United States)

    Han, Wenjing; Coutinho, Eduardo; Ruan, Huabin; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

    2016-01-01

    Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances.

  6. Mutual learning in a tree parity machine and its application to cryptography

    International Nuclear Information System (INIS)

    Rosen-Zvi, Michal; Klein, Einat; Kanter, Ido; Kinzel, Wolfgang

    2002-01-01

    Mutual learning of a pair of tree parity machines with continuous and discrete weight vectors is studied analytically. The analysis is based on a mapping procedure that maps the mutual learning in tree parity machines onto mutual learning in noisy perceptrons. The stationary solution of the mutual learning in the case of continuous tree parity machines depends on the learning rate where a phase transition from partial to full synchronization is observed. In the discrete case the learning process is based on a finite increment and a full synchronized state is achieved in a finite number of steps. The synchronization of discrete parity machines is introduced in order to construct an ephemeral key-exchange protocol. The dynamic learning of a third tree parity machine (an attacker) that tries to imitate one of the two machines while the two still update their weight vectors is also analyzed. In particular, the synchronization times of the naive attacker and the flipping attacker recently introduced in Ref. 9 are analyzed. All analytical results are found to be in good agreement with simulation results

  7. Tree Species Classification in Temperate Forests Using Formosat-2 Satellite Image Time Series

    Directory of Open Access Journals (Sweden)

    David Sheeren

    2016-09-01

    Full Text Available Mapping forest composition is a major concern for forest management, biodiversity assessment and for understanding the potential impacts of climate change on tree species distribution. In this study, the suitability of a dense high spatial resolution multispectral Formosat-2 satellite image time-series (SITS to discriminate tree species in temperate forests is investigated. Based on a 17-date SITS acquired across one year, thirteen major tree species (8 broadleaves and 5 conifers are classified in a study area of southwest France. The performance of parametric (GMM and nonparametric (k-NN, RF, SVM methods are compared at three class hierarchy levels for different versions of the SITS: (i a smoothed noise-free version based on the Whittaker smoother; (ii a non-smoothed cloudy version including all the dates; (iii a non-smoothed noise-free version including only 14 dates. Noise refers to pixels contaminated by clouds and cloud shadows. The results of the 108 distinct classifications show a very high suitability of the SITS to identify the forest tree species based on phenological differences (average κ = 0 . 93 estimated by cross-validation based on 1235 field-collected plots. SVM is found to be the best classifier with very close results from the other classifiers. No clear benefit of removing noise by smoothing can be observed. Classification accuracy is even improved using the non-smoothed cloudy version of the SITS compared to the 14 cloud-free image time series. However conclusions of the results need to be considered with caution because of possible overfitting. Disagreements also appear between the maps produced by the classifiers for complex mixed forests, suggesting a higher classification uncertainty in these contexts. Our findings suggest that time-series data can be a good alternative to hyperspectral data for mapping forest types. It also demonstrates the potential contribution of the recently launched Sentinel-2 satellite for

  8. Modeling Ecosystem Services for Park Trees: Sensitivity of i-Tree Eco Simulations to Light Exposure and Tree Species Classification

    Directory of Open Access Journals (Sweden)

    Rocco Pace

    2018-02-01

    Full Text Available Ecosystem modeling can help decision making regarding planting of urban trees for climate change mitigation and air pollution reduction. Algorithms and models that link the properties of plant functional types, species groups, or single species to their impact on specific ecosystem services have been developed. However, these models require a considerable effort for initialization that is inherently related to uncertainties originating from the high diversity of plant species in urban areas. We therefore suggest a new automated method to be used with the i-Tree Eco model to derive light competition for individual trees and investigate the importance of this property. Since competition depends also on the species, which is difficult to determine from increasingly used remote sensing methodologies, we also investigate the impact of uncertain tree species classification on the ecosystem services by comparing a species-specific inventory determined by field observation with a genus-specific categorization and a model initialization for the dominant deciduous and evergreen species only. Our results show how the simulation of competition affects the determination of carbon sequestration, leaf area, and related ecosystem services and that the proposed method provides a tool for improving estimations. Misclassifications of tree species can lead to large deviations in estimates of ecosystem impacts, particularly concerning biogenic volatile compound emissions. In our test case, monoterpene emissions almost doubled and isoprene emissions decreased to less than 10% when species were estimated to belong only to either two groups instead of being determined by species or genus. It is discussed that this uncertainty of emission estimates propagates further uncertainty in the estimation of potential ozone formation. Overall, we show the importance of using an individual light competition approach and explicitly parameterizing all ecosystem functions at the

  9. Advanced Steel Microstructural Classification by Deep Learning Methods.

    Science.gov (United States)

    Azimi, Seyed Majid; Britz, Dominik; Engstler, Michael; Fritz, Mario; Mücklich, Frank

    2018-02-01

    The inner structure of a material is called microstructure. It stores the genesis of a material and determines all its physical and chemical properties. While microstructural characterization is widely spread and well known, the microstructural classification is mostly done manually by human experts, which gives rise to uncertainties due to subjectivity. Since the microstructure could be a combination of different phases or constituents with complex substructures its automatic classification is very challenging and only a few prior studies exist. Prior works focused on designed and engineered features by experts and classified microstructures separately from the feature extraction step. Recently, Deep Learning methods have shown strong performance in vision applications by learning the features from data together with the classification step. In this work, we propose a Deep Learning method for microstructural classification in the examples of certain microstructural constituents of low carbon steel. This novel method employs pixel-wise segmentation via Fully Convolutional Neural Network (FCNN) accompanied by a max-voting scheme. Our system achieves 93.94% classification accuracy, drastically outperforming the state-of-the-art method of 48.89% accuracy. Beyond the strong performance of our method, this line of research offers a more robust and first of all objective way for the difficult task of steel quality appreciation.

  10. Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery.

    Science.gov (United States)

    Montella, Alfonso; Aria, Massimo; D'Ambrosio, Antonio; Mauriello, Filomena

    2012-11-01

    Aim of the study was the analysis of powered two-wheeler (PTW) crashes in Italy in order to detect interdependence as well as dissimilarities among crash characteristics and provide insights for the development of safety improvement strategies focused on PTWs. At this aim, data mining techniques were used to analyze the data relative to the 254,575 crashes involving PTWs occurred in Italy in the period 2006-2008. Classification trees analysis and rules discovery were performed. Tree-based methods are non-linear and non-parametric data mining tools for supervised classification and regression problems. They do not require a priori probabilistic knowledge about the phenomena under studying and consider conditional interactions among input data. Rules discovery is the identification of sets of items (i.e., crash patterns) that occur together in a given event (i.e., a crash in our study) more often than they would if they were independent of each other. Thus, the method can detect interdependence among crash characteristics. Due to the large number of patterns considered, both methods suffer from an extreme risk of finding patterns that appear due to chance alone. To overcome this problem, in our study we randomly split the sample data in two data sets and used well-established statistical practices to evaluate the statistical significance of the results. Both the classification trees and the rules discovery were effective in providing meaningful insights about PTW crash characteristics and their interdependencies. Even though in several cases different crash characteristics were highlighted, the results of the two the analysis methods were never contradictory. Furthermore, most of the findings of this study were consistent with the results of previous studies which used different analytical techniques, such as probabilistic models of crash injury severity. Basing on the analysis results, engineering countermeasures and policy initiatives to reduce PTW injuries and

  11. Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features.

    Science.gov (United States)

    Mudali, D; Teune, L K; Renken, R J; Leenders, K L; Roerdink, J B T M

    2015-01-01

    Medical imaging techniques like fluorodeoxyglucose positron emission tomography (FDG-PET) have been used to aid in the differential diagnosis of neurodegenerative brain diseases. In this study, the objective is to classify FDG-PET brain scans of subjects with Parkinsonian syndromes (Parkinson's disease, multiple system atrophy, and progressive supranuclear palsy) compared to healthy controls. The scaled subprofile model/principal component analysis (SSM/PCA) method was applied to FDG-PET brain image data to obtain covariance patterns and corresponding subject scores. The latter were used as features for supervised classification by the C4.5 decision tree method. Leave-one-out cross validation was applied to determine classifier performance. We carried out a comparison with other types of classifiers. The big advantage of decision tree classification is that the results are easy to understand by humans. A visual representation of decision trees strongly supports the interpretation process, which is very important in the context of medical diagnosis. Further improvements are suggested based on enlarging the number of the training data, enhancing the decision tree method by bagging, and adding additional features based on (f)MRI data.

  12. Learning Type Extension Trees for Metal Bonding State Prediction

    DEFF Research Database (Denmark)

    Frasconi, Paolo; Jaeger, Manfred; Passerini, Andrea

    2008-01-01

    Type Extension Trees (TET) have been recently introduced as an expressive representation language allowing to encode complex combinatorial features of relational entities. They can be efficiently learned with a greedy search strategy driven by a generalized relational information gain and a discr......Type Extension Trees (TET) have been recently introduced as an expressive representation language allowing to encode complex combinatorial features of relational entities. They can be efficiently learned with a greedy search strategy driven by a generalized relational information gain...

  13. QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.

    Science.gov (United States)

    Zwartjes, Ardjan; Havinga, Paul J M; Smit, Gerard J M; Hurink, Johann L

    2016-10-01

    In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.

  14. Machine learning algorithms for meteorological event classification in the coastal area using in-situ data

    Science.gov (United States)

    Sokolov, Anton; Gengembre, Cyril; Dmitriev, Egor; Delbarre, Hervé

    2017-04-01

    The problem is considered of classification of local atmospheric meteorological events in the coastal area such as sea breezes, fogs and storms. The in-situ meteorological data as wind speed and direction, temperature, humidity and turbulence are used as predictors. Local atmospheric events of 2013-2014 were analysed manually to train classification algorithms in the coastal area of English Channel in Dunkirk (France). Then, ultrasonic anemometer data and LIDAR wind profiler data were used as predictors. A few algorithms were applied to determine meteorological events by local data such as a decision tree, the nearest neighbour classifier, a support vector machine. The comparison of classification algorithms was carried out, the most important predictors for each event type were determined. It was shown that in more than 80 percent of the cases machine learning algorithms detect the meteorological class correctly. We expect that this methodology could be applied also to classify events by climatological in-situ data or by modelling data. It allows estimating frequencies of each event in perspective of climate change.

  15. Quantum Ensemble Classification: A Sampling-Based Learning Control Approach.

    Science.gov (United States)

    Chen, Chunlin; Dong, Daoyi; Qi, Bo; Petersen, Ian R; Rabitz, Herschel

    2017-06-01

    Quantum ensemble classification (QEC) has significant applications in discrimination of atoms (or molecules), separation of isotopes, and quantum information extraction. However, quantum mechanics forbids deterministic discrimination among nonorthogonal states. The classification of inhomogeneous quantum ensembles is very challenging, since there exist variations in the parameters characterizing the members within different classes. In this paper, we recast QEC as a supervised quantum learning problem. A systematic classification methodology is presented by using a sampling-based learning control (SLC) approach for quantum discrimination. The classification task is accomplished via simultaneously steering members belonging to different classes to their corresponding target states (e.g., mutually orthogonal states). First, a new discrimination method is proposed for two similar quantum systems. Then, an SLC method is presented for QEC. Numerical results demonstrate the effectiveness of the proposed approach for the binary classification of two-level quantum ensembles and the multiclass classification of multilevel quantum ensembles.

  16. Classification of Polarimetric SAR Data Using Dictionary Learning

    DEFF Research Database (Denmark)

    Vestergaard, Jacob Schack; Nielsen, Allan Aasbjerg; Dahl, Anders Lindbjerg

    2012-01-01

    This contribution deals with classification of multilook fully polarimetric synthetic aperture radar (SAR) data by learning a dictionary of crop types present in the Foulum test site. The Foulum test site contains a large number of agricultural fields, as well as lakes, forests, natural vegetation......, grasslands and urban areas, which make it ideally suited for evaluation of classification algorithms. Dictionary learning centers around building a collection of image patches typical for the classification problem at hand. This requires initial manual labeling of the classes present in the data and is thus...... a method for supervised classification. Sparse coding of these image patches aims to maintain a proficient number of typical patches and associated labels. Data is consecutively classified by a nearest neighbor search of the dictionary elements and labeled with probabilities of each class. Each dictionary...

  17. Learning about the internal structure of categories through classification and feature inference.

    Science.gov (United States)

    Jee, Benjamin D; Wiley, Jennifer

    2014-01-01

    Previous research on category learning has found that classification tasks produce representations that are skewed toward diagnostic feature dimensions, whereas feature inference tasks lead to richer representations of within-category structure. Yet, prior studies often measure category knowledge through tasks that involve identifying only the typical features of a category. This neglects an important aspect of a category's internal structure: how typical and atypical features are distributed within a category. The present experiments tested the hypothesis that inference learning results in richer knowledge of internal category structure than classification learning. We introduced several new measures to probe learners' representations of within-category structure. Experiment 1 found that participants in the inference condition learned and used a wider range of feature dimensions than classification learners. Classification learners, however, were more sensitive to the presence of atypical features within categories. Experiment 2 provided converging evidence that classification learners were more likely to incorporate atypical features into their representations. Inference learners were less likely to encode atypical category features, even in a "partial inference" condition that focused learners' attention on the feature dimensions relevant to classification. Overall, these results are contrary to the hypothesis that inference learning produces superior knowledge of within-category structure. Although inference learning promoted representations that included a broad range of category-typical features, classification learning promoted greater sensitivity to the distribution of typical and atypical features within categories.

  18. Attribute Learning for SAR Image Classification

    Directory of Open Access Journals (Sweden)

    Chu He

    2017-04-01

    Full Text Available This paper presents a classification approach based on attribute learning for high spatial resolution Synthetic Aperture Radar (SAR images. To explore the representative and discriminative attributes of SAR images, first, an iterative unsupervised algorithm is designed to cluster in the low-level feature space, where the maximum edge response and the ratio of mean-to-variance are included; a cross-validation step is applied to prevent overfitting. Second, the most discriminative clustering centers are sorted out to construct an attribute dictionary. By resorting to the attribute dictionary, a representation vector describing certain categories in the SAR image can be generated, which in turn is used to perform the classifying task. The experiments conducted on TerraSAR-X images indicate that those learned attributes have strong visual semantics, which are characterized by bright and dark spots, stripes, or their combinations. The classification method based on these learned attributes achieves better results.

  19. Cooperative Learning for Distributed In-Network Traffic Classification

    Science.gov (United States)

    Joseph, S. B.; Loo, H. R.; Ismail, I.; Andromeda, T.; Marsono, M. N.

    2017-04-01

    Inspired by the concept of autonomic distributed/decentralized network management schemes, we consider the issue of information exchange among distributed network nodes to network performance and promote scalability for in-network monitoring. In this paper, we propose a cooperative learning algorithm for propagation and synchronization of network information among autonomic distributed network nodes for online traffic classification. The results show that network nodes with sharing capability perform better with a higher average accuracy of 89.21% (sharing data) and 88.37% (sharing clusters) compared to 88.06% for nodes without cooperative learning capability. The overall performance indicates that cooperative learning is promising for distributed in-network traffic classification.

  20. Learning decision trees with flexible constraints and objectives using integer optimization

    NARCIS (Netherlands)

    Verwer, S.; Zhang, Y.

    2017-01-01

    We encode the problem of learning the optimal decision tree of a given depth as an integer optimization problem. We show experimentally that our method (DTIP) can be used to learn good trees up to depth 5 from data sets of size up to 1000. In addition to being efficient, our new formulation allows

  1. Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks.

    Science.gov (United States)

    Joshi, Vinayak S; Reinhardt, Joseph M; Garvin, Mona K; Abramoff, Michael D

    2014-01-01

    The separation of the retinal vessel network into distinct arterial and venous vessel trees is of high interest. We propose an automated method for identification and separation of retinal vessel trees in a retinal color image by converting a vessel segmentation image into a vessel segment map and identifying the individual vessel trees by graph search. Orientation, width, and intensity of each vessel segment are utilized to find the optimal graph of vessel segments. The separated vessel trees are labeled as primary vessel or branches. We utilize the separated vessel trees for arterial-venous (AV) classification, based on the color properties of the vessels in each tree graph. We applied our approach to a dataset of 50 fundus images from 50 subjects. The proposed method resulted in an accuracy of 91.44% correctly classified vessel pixels as either artery or vein. The accuracy of correctly classified major vessel segments was 96.42%.

  2. TREE SPECIES CLASSIFICATION OF BROADLEAVED FORESTS IN NAGANO, CENTRAL JAPAN, USING AIRBORNE LASER DATA AND MULTISPECTRAL IMAGES

    Directory of Open Access Journals (Sweden)

    S. Deng

    2017-10-01

    Full Text Available This study attempted to classify three coniferous and ten broadleaved tree species by combining airborne laser scanning (ALS data and multispectral images. The study area, located in Nagano, central Japan, is within the broadleaved forests of the Afan Woodland area. A total of 235 trees were surveyed in 2016, and we recorded the species, DBH, and tree height. The geographical position of each tree was collected using a Global Navigation Satellite System (GNSS device. Tree crowns were manually detected using GNSS position data, field photographs, true-color orthoimages with three bands (red-green-blue, RGB, 3D point clouds, and a canopy height model derived from ALS data. Then a total of 69 features, including 27 image-based and 42 point-based features, were extracted from the RGB images and the ALS data to classify tree species. Finally, the detected tree crowns were classified into two classes for the first level (coniferous and broadleaved trees, four classes for the second level (Pinus densiflora, Larix kaempferi, Cryptomeria japonica, and broadleaved trees, and 13 classes for the third level (three coniferous and ten broadleaved species, using the 27 image-based features, 42 point-based features, all 69 features, and the best combination of features identified using a neighborhood component analysis algorithm, respectively. The overall classification accuracies reached 90 % at the first and second levels but less than 60 % at the third level. The classifications using the best combinations of features had higher accuracies than those using the image-based and point-based features and the combination of all of the 69 features.

  3. Classification of Strawberry Fruit Shape by Machine Learning

    Science.gov (United States)

    Ishikawa, T.; Hayashi, A.; Nagamatsu, S.; Kyutoku, Y.; Dan, I.; Wada, T.; Oku, K.; Saeki, Y.; Uto, T.; Tanabata, T.; Isobe, S.; Kochi, N.

    2018-05-01

    Shape is one of the most important traits of agricultural products due to its relationships with the quality, quantity, and value of the products. For strawberries, the nine types of fruit shape were defined and classified by humans based on the sampler patterns of the nine types. In this study, we tested the classification of strawberry shapes by machine learning in order to increase the accuracy of the classification, and we introduce the concept of computerization into this field. Four types of descriptors were extracted from the digital images of strawberries: (1) the Measured Values (MVs) including the length of the contour line, the area, the fruit length and width, and the fruit width/length ratio; (2) the Ellipse Similarity Index (ESI); (3) Elliptic Fourier Descriptors (EFDs), and (4) Chain Code Subtraction (CCS). We used these descriptors for the classification test along with the random forest approach, and eight of the nine shape types were classified with combinations of MVs + CCS + EFDs. CCS is a descriptor that adds human knowledge to the chain codes, and it showed higher robustness in classification than the other descriptors. Our results suggest machine learning's high ability to classify fruit shapes accurately. We will attempt to increase the classification accuracy and apply the machine learning methods to other plant species.

  4. Hyper-parameter tuning of a decision tree induction algorithm

    NARCIS (Netherlands)

    Mantovani, R.G.; Horváth, T.; Cerri, R.; Vanschoren, J.; de Carvalho, A.C.P.L.F.

    2017-01-01

    Supervised classification is the most studied task in Machine Learning. Among the many algorithms used in such task, Decision Tree algorithms are a popular choice, since they are robust and efficient to construct. Moreover, they have the advantage of producing comprehensible models and satisfactory

  5. Empirical Studies On Machine Learning Based Text Classification Algorithms

    OpenAIRE

    Shweta C. Dharmadhikari; Maya Ingle; Parag Kulkarni

    2011-01-01

    Automatic classification of text documents has become an important research issue now days. Properclassification of text documents requires information retrieval, machine learning and Natural languageprocessing (NLP) techniques. Our aim is to focus on important approaches to automatic textclassification based on machine learning techniques viz. supervised, unsupervised and semi supervised.In this paper we present a review of various text classification approaches under machine learningparadig...

  6. Discriminative Bayesian Dictionary Learning for Classification.

    Science.gov (United States)

    Akhtar, Naveed; Shafait, Faisal; Mian, Ajmal

    2016-12-01

    We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a finite approximation of Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches.

  7. Building classification trees to explain the radioactive contamination levels of the plants; Construction d'arbres de discrimination pour expliquer les niveaux de contamination radioactive des vegetaux

    Energy Technology Data Exchange (ETDEWEB)

    Briand, B

    2008-04-15

    The objective of this thesis is the development of a method allowing the identification of factors leading to various radioactive contamination levels of the plants. The methodology suggested is based on the use of a radioecological transfer model of the radionuclides through the environment (A.S.T.R.A.L. computer code) and a classification-tree method. Particularly, to avoid the instability problems of classification trees and to preserve the tree structure, a node level stabilizing technique is used. Empirical comparisons are carried out between classification trees built by this method (called R.E.N. method) and those obtained by the C.A.R.T. method. A similarity measure is defined to compare the structure of two classification trees. This measure is used to study the stabilizing performance of the R.E.N. method. The methodology suggested is applied to a simplified contamination scenario. By the results obtained, we can identify the main variables responsible of the various radioactive contamination levels of four leafy-vegetables (lettuce, cabbage, spinach and leek). Some extracted rules from these classification trees can be usable in a post-accidental context. (author)

  8. QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms

    Directory of Open Access Journals (Sweden)

    Ardjan Zwartjes

    2016-10-01

    Full Text Available In this work, we introduce QUEST (QUantile Estimation after Supervised Training, an adaptive classification algorithm for Wireless Sensor Networks (WSNs that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.

  9. Classification of multiple sclerosis lesions using adaptive dictionary learning.

    Science.gov (United States)

    Deshpande, Hrishikesh; Maurel, Pierre; Barillot, Christian

    2015-12-01

    This paper presents a sparse representation and an adaptive dictionary learning based method for automated classification of multiple sclerosis (MS) lesions in magnetic resonance (MR) images. Manual delineation of MS lesions is a time-consuming task, requiring neuroradiology experts to analyze huge volume of MR data. This, in addition to the high intra- and inter-observer variability necessitates the requirement of automated MS lesion classification methods. Among many image representation models and classification methods that can be used for such purpose, we investigate the use of sparse modeling. In the recent years, sparse representation has evolved as a tool in modeling data using a few basis elements of an over-complete dictionary and has found applications in many image processing tasks including classification. We propose a supervised classification approach by learning dictionaries specific to the lesions and individual healthy brain tissues, which include white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The size of the dictionaries learned for each class plays a major role in data representation but it is an even more crucial element in the case of competitive classification. Our approach adapts the size of the dictionary for each class, depending on the complexity of the underlying data. The algorithm is validated using 52 multi-sequence MR images acquired from 13 MS patients. The results demonstrate the effectiveness of our approach in MS lesion classification. Copyright © 2015 Elsevier Ltd. All rights reserved.

  10. Applying Active Learning to Assertion Classification of Concepts in Clinical Text

    Science.gov (United States)

    Chen, Yukun; Mani, Subramani; Xu, Hua

    2012-01-01

    Supervised machine learning methods for clinical natural language processing (NLP) research require a large number of annotated samples, which are very expensive to build because of the involvement of physicians. Active learning, an approach that actively samples from a large pool, provides an alternative solution. Its major goal in classification is to reduce the annotation effort while maintaining the quality of the predictive model. However, few studies have investigated its uses in clinical NLP. This paper reports an application of active learning to a clinical text classification task: to determine the assertion status of clinical concepts. The annotated corpus for the assertion classification task in the 2010 i2b2/VA Clinical NLP Challenge was used in this study. We implemented several existing and newly developed active learning algorithms and assessed their uses. The outcome is reported in the global ALC score, based on the Area under the average Learning Curve of the AUC (Area Under the Curve) score. Results showed that when the same number of annotated samples was used, active learning strategies could generate better classification models (best ALC – 0.7715) than the passive learning method (random sampling) (ALC – 0.7411). Moreover, to achieve the same classification performance, active learning strategies required fewer samples than the random sampling method. For example, to achieve an AUC of 0.79, the random sampling method used 32 samples, while our best active learning algorithm required only 12 samples, a reduction of 62.5% in manual annotation effort. PMID:22127105

  11. A rule-learning program in high energy physics event classification

    International Nuclear Information System (INIS)

    Clearwater, S.H.; Stern, E.G.

    1991-01-01

    We have applied a rule-learning program to the problem of event classification in high energy physics. The program searches for event classifications, i.e. rules, and effectively allows an exploration of many more possible classifications than is practical by a physicist. The program, RL4, is particularly useful because it can easily explore multi-dimensional rules as well as rules that may seem non-intuitive at first to the physicist. RL4 is also contrasted with other learning programs. (orig.)

  12. Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier.

    Science.gov (United States)

    Kambhampati, Satya Samyukta; Singh, Vishal; Manikandan, M Sabarimalai; Ramkumar, Barathram

    2015-08-01

    In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

  13. Research on Classification of Chinese Text Data Based on SVM

    Science.gov (United States)

    Lin, Yuan; Yu, Hongzhi; Wan, Fucheng; Xu, Tao

    2017-09-01

    Data Mining has important application value in today’s industry and academia. Text classification is a very important technology in data mining. At present, there are many mature algorithms for text classification. KNN, NB, AB, SVM, decision tree and other classification methods all show good classification performance. Support Vector Machine’ (SVM) classification method is a good classifier in machine learning research. This paper will study the classification effect based on the SVM method in the Chinese text data, and use the support vector machine method in the chinese text to achieve the classify chinese text, and to able to combination of academia and practical application.

  14. Woodland Mapping at Single-Tree Levels Using Object-Oriented Classification of Unmanned Aerial Vehicle (uav) Images

    Science.gov (United States)

    Chenari, A.; Erfanifard, Y.; Dehghani, M.; Pourghasemi, H. R.

    2017-09-01

    Remotely sensed datasets offer a reliable means to precisely estimate biophysical characteristics of individual species sparsely distributed in open woodlands. Moreover, object-oriented classification has exhibited significant advantages over different classification methods for delineation of tree crowns and recognition of species in various types of ecosystems. However, it still is unclear if this widely-used classification method can have its advantages on unmanned aerial vehicle (UAV) digital images for mapping vegetation cover at single-tree levels. In this study, UAV orthoimagery was classified using object-oriented classification method for mapping a part of wild pistachio nature reserve in Zagros open woodlands, Fars Province, Iran. This research focused on recognizing two main species of the study area (i.e., wild pistachio and wild almond) and estimating their mean crown area. The orthoimage of study area was consisted of 1,076 images with spatial resolution of 3.47 cm which was georeferenced using 12 ground control points (RMSE=8 cm) gathered by real-time kinematic (RTK) method. The results showed that the UAV orthoimagery classified by object-oriented method efficiently estimated mean crown area of wild pistachios (52.09±24.67 m2) and wild almonds (3.97±1.69 m2) with no significant difference with their observed values (α=0.05). In addition, the results showed that wild pistachios (accuracy of 0.90 and precision of 0.92) and wild almonds (accuracy of 0.90 and precision of 0.89) were well recognized by image segmentation. In general, we concluded that UAV orthoimagery can efficiently produce precise biophysical data of vegetation stands at single-tree levels, which therefore is suitable for assessment and monitoring open woodlands.

  15. A supervised learning rule for classification of spatiotemporal spike patterns.

    Science.gov (United States)

    Lilin Guo; Zhenzhong Wang; Adjouadi, Malek

    2016-08-01

    This study introduces a novel supervised algorithm for spiking neurons that take into consideration synapse delays and axonal delays associated with weights. It can be utilized for both classification and association and uses several biologically influenced properties, such as axonal and synaptic delays. This algorithm also takes into consideration spike-timing-dependent plasticity as in Remote Supervised Method (ReSuMe). This paper focuses on the classification aspect alone. Spiked neurons trained according to this proposed learning rule are capable of classifying different categories by the associated sequences of precisely timed spikes. Simulation results have shown that the proposed learning method greatly improves classification accuracy when compared to the Spike Pattern Association Neuron (SPAN) and the Tempotron learning rule.

  16. Multispectral imaging burn wound tissue classification system: a comparison of test accuracies between several common machine learning algorithms

    Science.gov (United States)

    Squiers, John J.; Li, Weizhi; King, Darlene R.; Mo, Weirong; Zhang, Xu; Lu, Yang; Sellke, Eric W.; Fan, Wensheng; DiMaio, J. Michael; Thatcher, Jeffrey E.

    2016-03-01

    The clinical judgment of expert burn surgeons is currently the standard on which diagnostic and therapeutic decisionmaking regarding burn injuries is based. Multispectral imaging (MSI) has the potential to increase the accuracy of burn depth assessment and the intraoperative identification of viable wound bed during surgical debridement of burn injuries. A highly accurate classification model must be developed using machine-learning techniques in order to translate MSI data into clinically-relevant information. An animal burn model was developed to build an MSI training database and to study the burn tissue classification ability of several models trained via common machine-learning algorithms. The algorithms tested, from least to most complex, were: K-nearest neighbors (KNN), decision tree (DT), linear discriminant analysis (LDA), weighted linear discriminant analysis (W-LDA), quadratic discriminant analysis (QDA), ensemble linear discriminant analysis (EN-LDA), ensemble K-nearest neighbors (EN-KNN), and ensemble decision tree (EN-DT). After the ground-truth database of six tissue types (healthy skin, wound bed, blood, hyperemia, partial injury, full injury) was generated by histopathological analysis, we used 10-fold cross validation to compare the algorithms' performances based on their accuracies in classifying data against the ground truth, and each algorithm was tested 100 times. The mean test accuracy of the algorithms were KNN 68.3%, DT 61.5%, LDA 70.5%, W-LDA 68.1%, QDA 68.9%, EN-LDA 56.8%, EN-KNN 49.7%, and EN-DT 36.5%. LDA had the highest test accuracy, reflecting the bias-variance tradeoff over the range of complexities inherent to the algorithms tested. Several algorithms were able to match the current standard in burn tissue classification, the clinical judgment of expert burn surgeons. These results will guide further development of an MSI burn tissue classification system. Given that there are few surgeons and facilities specializing in burn care

  17. Using spectrotemporal indices to improve the fruit-tree crop classification accuracy

    Science.gov (United States)

    Peña, M. A.; Liao, R.; Brenning, A.

    2017-06-01

    This study assesses the potential of spectrotemporal indices derived from satellite image time series (SITS) to improve the classification accuracy of fruit-tree crops. Six major fruit-tree crop types in the Aconcagua Valley, Chile, were classified by applying various linear discriminant analysis (LDA) techniques on a Landsat-8 time series of nine images corresponding to the 2014-15 growing season. As features we not only used the complete spectral resolution of the SITS, but also all possible normalized difference indices (NDIs) that can be constructed from any two bands of the time series, a novel approach to derive features from SITS. Due to the high dimensionality of this "enhanced" feature set we used the lasso and ridge penalized variants of LDA (PLDA). Although classification accuracies yielded by the standard LDA applied on the full-band SITS were good (misclassification error rate, MER = 0.13), they were further improved by 23% (MER = 0.10) with ridge PLDA using the enhanced feature set. The most important bands to discriminate the crops of interest were mainly concentrated on the first two image dates of the time series, corresponding to the crops' greenup stage. Despite the high predictor weights provided by the red and near infrared bands, typically used to construct greenness spectral indices, other spectral regions were also found important for the discrimination, such as the shortwave infrared band at 2.11-2.19 μm, sensitive to foliar water changes. These findings support the usefulness of spectrotemporal indices in the context of SITS-based crop type classifications, which until now have been mainly constructed by the arithmetic combination of two bands of the same image date in order to derive greenness temporal profiles like those from the normalized difference vegetation index.

  18. Prediction of survival to discharge following cardiopulmonary resuscitation using classification and regression trees.

    Science.gov (United States)

    Ebell, Mark H; Afonso, Anna M; Geocadin, Romergryko G

    2013-12-01

    To predict the likelihood that an inpatient who experiences cardiopulmonary arrest and undergoes cardiopulmonary resuscitation survives to discharge with good neurologic function or with mild deficits (Cerebral Performance Category score = 1). Classification and Regression Trees were used to develop branching algorithms that optimize the ability of a series of tests to correctly classify patients into two or more groups. Data from 2007 to 2008 (n = 38,092) were used to develop candidate Classification and Regression Trees models to predict the outcome of inpatient cardiopulmonary resuscitation episodes and data from 2009 (n = 14,435) to evaluate the accuracy of the models and judge the degree of over fitting. Both supervised and unsupervised approaches to model development were used. 366 hospitals participating in the Get With the Guidelines-Resuscitation registry. Adult inpatients experiencing an index episode of cardiopulmonary arrest and undergoing cardiopulmonary resuscitation in the hospital. The five candidate models had between 8 and 21 nodes and an area under the receiver operating characteristic curve from 0.718 to 0.766 in the derivation group and from 0.683 to 0.746 in the validation group. One of the supervised models had 14 nodes and classified 27.9% of patients as very unlikely to survive neurologically intact or with mild deficits (Tree models that predict survival to discharge with good neurologic function or with mild deficits following in-hospital cardiopulmonary arrest. Models like this can assist physicians and patients who are considering do-not-resuscitate orders.

  19. A classification model of Hyperion image base on SAM combined decision tree

    Science.gov (United States)

    Wang, Zhenghai; Hu, Guangdao; Zhou, YongZhang; Liu, Xin

    2009-10-01

    Monitoring the Earth using imaging spectrometers has necessitated more accurate analyses and new applications to remote sensing. A very high dimensional input space requires an exponentially large amount of data to adequately and reliably represent the classes in that space. On the other hand, with increase in the input dimensionality the hypothesis space grows exponentially, which makes the classification performance highly unreliable. Traditional classification algorithms Classification of hyperspectral images is challenging. New algorithms have to be developed for hyperspectral data classification. The Spectral Angle Mapper (SAM) is a physically-based spectral classification that uses an ndimensional angle to match pixels to reference spectra. The algorithm determines the spectral similarity between two spectra by calculating the angle between the spectra, treating them as vectors in a space with dimensionality equal to the number of bands. The key and difficulty is that we should artificial defining the threshold of SAM. The classification precision depends on the rationality of the threshold of SAM. In order to resolve this problem, this paper proposes a new automatic classification model of remote sensing image using SAM combined with decision tree. It can automatic choose the appropriate threshold of SAM and improve the classify precision of SAM base on the analyze of field spectrum. The test area located in Heqing Yunnan was imaged by EO_1 Hyperion imaging spectrometer using 224 bands in visual and near infrared. The area included limestone areas, rock fields, soil and forests. The area was classified into four different vegetation and soil types. The results show that this method choose the appropriate threshold of SAM and eliminates the disturbance and influence of unwanted objects effectively, so as to improve the classification precision. Compared with the likelihood classification by field survey data, the classification precision of this model

  20. Sentiment classification of Roman-Urdu opinions using Naïve Bayesian, Decision Tree and KNN classification techniques

    Directory of Open Access Journals (Sweden)

    Muhammad Bilal

    2016-07-01

    Full Text Available Sentiment mining is a field of text mining to determine the attitude of people about a particular product, topic, politician in newsgroup posts, review sites, comments on facebook posts twitter, etc. There are many issues involved in opinion mining. One important issue is that opinions could be in different languages (English, Urdu, Arabic, etc.. To tackle each language according to its orientation is a challenging task. Most of the research work in sentiment mining has been done in English language. Currently, limited research is being carried out on sentiment classification of other languages like Arabic, Italian, Urdu and Hindi. In this paper, three classification models are used for text classification using Waikato Environment for Knowledge Analysis (WEKA. Opinions written in Roman-Urdu and English are extracted from a blog. These extracted opinions are documented in text files to prepare a training dataset containing 150 positive and 150 negative opinions, as labeled examples. Testing data set is supplied to three different models and the results in each case are analyzed. The results show that Naïve Bayesian outperformed Decision Tree and KNN in terms of more accuracy, precision, recall and F-measure.

  1. Comparing Methodologies for Developing an Early Warning System: Classification and Regression Tree Model versus Logistic Regression. REL 2015-077

    Science.gov (United States)

    Koon, Sharon; Petscher, Yaacov

    2015-01-01

    The purpose of this report was to explicate the use of logistic regression and classification and regression tree (CART) analysis in the development of early warning systems. It was motivated by state education leaders' interest in maintaining high classification accuracy while simultaneously improving practitioner understanding of the rules by…

  2. A strategy learning model for autonomous agents based on classification

    Directory of Open Access Journals (Sweden)

    Śnieżyński Bartłomiej

    2015-09-01

    Full Text Available In this paper we propose a strategy learning model for autonomous agents based on classification. In the literature, the most commonly used learning method in agent-based systems is reinforcement learning. In our opinion, classification can be considered a good alternative. This type of supervised learning can be used to generate a classifier that allows the agent to choose an appropriate action for execution. Experimental results show that this model can be successfully applied for strategy generation even if rewards are delayed. We compare the efficiency of the proposed model and reinforcement learning using the farmer-pest domain and configurations of various complexity. In complex environments, supervised learning can improve the performance of agents much faster that reinforcement learning. If an appropriate knowledge representation is used, the learned knowledge may be analyzed by humans, which allows tracking the learning process

  3. Automatic Hierarchical Color Image Classification

    Directory of Open Access Journals (Sweden)

    Jing Huang

    2003-02-01

    Full Text Available Organizing images into semantic categories can be extremely useful for content-based image retrieval and image annotation. Grouping images into semantic classes is a difficult problem, however. Image classification attempts to solve this hard problem by using low-level image features. In this paper, we propose a method for hierarchical classification of images via supervised learning. This scheme relies on using a good low-level feature and subsequently performing feature-space reconfiguration using singular value decomposition to reduce noise and dimensionality. We use the training data to obtain a hierarchical classification tree that can be used to categorize new images. Our experimental results suggest that this scheme not only performs better than standard nearest-neighbor techniques, but also has both storage and computational advantages.

  4. From Google Maps to a fine-grained catalog of street trees

    Science.gov (United States)

    Branson, Steve; Wegner, Jan Dirk; Hall, David; Lang, Nico; Schindler, Konrad; Perona, Pietro

    2018-01-01

    Up-to-date catalogs of the urban tree population are of importance for municipalities to monitor and improve quality of life in cities. Despite much research on automation of tree mapping, mainly relying on dedicated airborne LiDAR or hyperspectral campaigns, tree detection and species recognition is still mostly done manually in practice. We present a fully automated tree detection and species recognition pipeline that can process thousands of trees within a few hours using publicly available aerial and street view images of Google MapsTM. These data provide rich information from different viewpoints and at different scales from global tree shapes to bark textures. Our work-flow is built around a supervised classification that automatically learns the most discriminative features from thousands of trees and corresponding, publicly available tree inventory data. In addition, we introduce a change tracker that recognizes changes of individual trees at city-scale, which is essential to keep an urban tree inventory up-to-date. The system takes street-level images of the same tree location at two different times and classifies the type of change (e.g., tree has been removed). Drawing on recent advances in computer vision and machine learning, we apply convolutional neural networks (CNN) for all classification tasks. We propose the following pipeline: download all available panoramas and overhead images of an area of interest, detect trees per image and combine multi-view detections in a probabilistic framework, adding prior knowledge; recognize fine-grained species of detected trees. In a later, separate module, track trees over time, detect significant changes and classify the type of change. We believe this is the first work to exploit publicly available image data for city-scale street tree detection, species recognition and change tracking, exhaustively over several square kilometers, respectively many thousands of trees. Experiments in the city of Pasadena

  5. An Evaluation of Different Training Sample Allocation Schemes for Discrete and Continuous Land Cover Classification Using Decision Tree-Based Algorithms

    Directory of Open Access Journals (Sweden)

    René Roland Colditz

    2015-07-01

    Full Text Available Land cover mapping for large regions often employs satellite images of medium to coarse spatial resolution, which complicates mapping of discrete classes. Class memberships, which estimate the proportion of each class for every pixel, have been suggested as an alternative. This paper compares different strategies of training data allocation for discrete and continuous land cover mapping using classification and regression tree algorithms. In addition to measures of discrete and continuous map accuracy the correct estimation of the area is another important criteria. A subset of the 30 m national land cover dataset of 2006 (NLCD2006 of the United States was used as reference set to classify NADIR BRDF-adjusted surface reflectance time series of MODIS at 900 m spatial resolution. Results show that sampling of heterogeneous pixels and sample allocation according to the expected area of each class is best for classification trees. Regression trees for continuous land cover mapping should be trained with random allocation, and predictions should be normalized with a linear scaling function to correctly estimate the total area. From the tested algorithms random forest classification yields lower errors than boosted trees of C5.0, and Cubist shows higher accuracies than random forest regression.

  6. Automated Sleep Stage Scoring by Decision Tree Learning

    National Research Council Canada - National Science Library

    Hanaoka, Masaaki

    2001-01-01

    In this paper we describe a waveform recognition method that extracts characteristic parameters from wave- forms and a method of automated sleep stage scoring using decision tree learning that is in...

  7. WOODLAND MAPPING AT SINGLE-TREE LEVELS USING OBJECT-ORIENTED CLASSIFICATION OF UNMANNED AERIAL VEHICLE (UAV IMAGES

    Directory of Open Access Journals (Sweden)

    A. Chenari

    2017-09-01

    Full Text Available Remotely sensed datasets offer a reliable means to precisely estimate biophysical characteristics of individual species sparsely distributed in open woodlands. Moreover, object-oriented classification has exhibited significant advantages over different classification methods for delineation of tree crowns and recognition of species in various types of ecosystems. However, it still is unclear if this widely-used classification method can have its advantages on unmanned aerial vehicle (UAV digital images for mapping vegetation cover at single-tree levels. In this study, UAV orthoimagery was classified using object-oriented classification method for mapping a part of wild pistachio nature reserve in Zagros open woodlands, Fars Province, Iran. This research focused on recognizing two main species of the study area (i.e., wild pistachio and wild almond and estimating their mean crown area. The orthoimage of study area was consisted of 1,076 images with spatial resolution of 3.47 cm which was georeferenced using 12 ground control points (RMSE=8 cm gathered by real-time kinematic (RTK method. The results showed that the UAV orthoimagery classified by object-oriented method efficiently estimated mean crown area of wild pistachios (52.09±24.67 m2 and wild almonds (3.97±1.69 m2 with no significant difference with their observed values (α=0.05. In addition, the results showed that wild pistachios (accuracy of 0.90 and precision of 0.92 and wild almonds (accuracy of 0.90 and precision of 0.89 were well recognized by image segmentation. In general, we concluded that UAV orthoimagery can efficiently produce precise biophysical data of vegetation stands at single-tree levels, which therefore is suitable for assessment and monitoring open woodlands.

  8. ARABIC TEXT CLASSIFICATION USING NEW STEMMER FOR FEATURE SELECTION AND DECISION TREES

    Directory of Open Access Journals (Sweden)

    SAID BAHASSINE

    2017-06-01

    Full Text Available Text classification is the process of assignment of unclassified text to appropriate classes based on their content. The most prevalent representation for text classification is the bag of words vector. In this representation, the words that appear in documents often have multiple morphological structures, grammatical forms. In most cases, this morphological variant of words belongs to the same category. In the first part of this paper, anew stemming algorithm was developed in which each term of a given document is represented by its root. In the second part, a comparative study is conducted of the impact of two stemming algorithms namely Khoja’s stemmer and our new stemmer (referred to hereafter by origin-stemmer on Arabic text classification. This investigation was carried out using chi-square as a feature of selection to reduce the dimensionality of the feature space and decision tree classifier. In order to evaluate the performance of the classifier, this study used a corpus that consists of 5070 documents independently classified into six categories: sport, entertainment, business, Middle East, switch and world on WEKA toolkit. The recall, f-measure and precision measures are used to compare the performance of the obtained models. The experimental results show that text classification using rout stemmer outperforms classification using Khoja’s stemmer. The f-measure was 92.9% in sport category and 89.1% in business category.

  9. Classification and Progression Based on CFS-GA and C5.0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B.

    Science.gov (United States)

    Chen, Xiao Yu; Ma, Li Zhuang; Chu, Na; Zhou, Min; Hu, Yiyang

    2013-01-01

    Chronic hepatitis B (CHB) is a serious public health problem, and Traditional Chinese Medicine (TCM) plays an important role in the control and treatment for CHB. In the treatment of TCM, zheng discrimination is the most important step. In this paper, an approach based on CFS-GA (Correlation based Feature Selection and Genetic Algorithm) and C5.0 boost decision tree is used for zheng classification and progression in the TCM treatment of CHB. The CFS-GA performs better than the typical method of CFS. By CFS-GA, the acquired attribute subset is classified by C5.0 boost decision tree for TCM zheng classification of CHB, and C5.0 decision tree outperforms two typical decision trees of NBTree and REPTree on CFS-GA, CFS, and nonselection in comparison. Based on the critical indicators from C5.0 decision tree, important lab indicators in zheng progression are obtained by the method of stepwise discriminant analysis for expressing TCM zhengs in CHB, and alterations of the important indicators are also analyzed in zheng progression. In conclusion, all the three decision trees perform better on CFS-GA than on CFS and nonselection, and C5.0 decision tree outperforms the two typical decision trees both on attribute selection and nonselection.

  10. Examination as to the classification of representative tree species at Satoyama coppice forest using multiwavelength range data observed from aircraft

    International Nuclear Information System (INIS)

    Setojima, M.; Imai, Y.; Funahashi, M.; Kawai, M.; Katsuki, T.

    2006-01-01

    In this study, we examined the possibility of classifying representative tree species at Satoyama coppice forest based on spectral reflectance of the tree species. We used the airborne hyperspectral data observed in exhibition leaf stage at the test forest (about 3.4ha) in Tama Forest Science Garden (Hachioji, Tokyo) , where the forest type similar to that of Satoyama is preserved. The classification accuracy was verified by comparing the results of interpretation of color aerial photographs taken in spring and autumn in chronological order and the field survey. As a result, the 534-556 nm (band 6 and band 7) in the visible range and 739-762 nm (band 15 and band 16), 785nm (band 17) in the near infrared range are effective bands for classification of the species of such trees as Castanopsis sieboldii, Quercus glauca, Zelkova serrata, Quercus serrata, Cryptomeria japonica, and Chamaecyparis obutusa, which are representative trees in Satoyama coppice forest in Tama district

  11. Using machine learning, neural networks and statistics to predict bankruptcy

    NARCIS (Netherlands)

    Pompe, P.P.M.; Feelders, A.J.; Feelders, A.J.

    1997-01-01

    Recent literature strongly suggests that machine learning approaches to classification outperform "classical" statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees, and neural networks in predicting corporate bankruptcy. Linear

  12. Classification of Learning Styles in Virtual Learning Environment Using J48 Decision Tree

    Science.gov (United States)

    Maaliw, Renato R. III; Ballera, Melvin A.

    2017-01-01

    The usage of data mining has dramatically increased over the past few years and the education sector is leveraging this field in order to analyze and gain intuitive knowledge in terms of the vast accumulated data within its confines. The primary objective of this study is to compare the results of different classification techniques such as Naïve…

  13. Prognostic classification index in Iranian colorectal cancer patients: Survival tree analysis

    Directory of Open Access Journals (Sweden)

    Amal Saki Malehi

    2016-01-01

    Full Text Available Aims: The aim of this study was to determine the prognostic index for separating homogenous subgroups in colorectal cancer (CRC patients based on clinicopathological characteristics using survival tree analysis. Methods: The current study was conducted at the Research Center of Gastroenterology and Liver Disease, Shahid Beheshti Medical University in Tehran, between January 2004 and January 2009. A total of 739 patients who already have been diagnosed with CRC based on pathologic report were enrolled. The data included demographic and clinical-pathological characteristic of patients. Tree-structured survival analysis based on a recursive partitioning algorithm was implemented to evaluate prognostic factors. The probability curves were calculated according to the Kaplan-Meier method, and the hazard ratio was estimated as an interest effect size. Result: There were 526 males (71.2% of these patients. The mean survival time (from diagnosis time was 42.46± (3.4. Survival tree identified three variables as main prognostic factors and based on their four prognostic subgroups was constructed. The log-rank test showed good separation of survival curves. Patients with Stage I-IIIA and treated with surgery as the first treatment showed low risk (median = 34 months whereas patients with stage IIIB, IV, and more than 68 years have the worse survival outcome (median = 9.5 months. Conclusion: Constructing the prognostic classification index via survival tree can aid the researchers to assess interaction between clinical variables and determining the cumulative effect of these variables on survival outcome.

  14. Imitation learning of car driving skills with decision trees and random forests

    Directory of Open Access Journals (Sweden)

    Cichosz Paweł

    2014-09-01

    Full Text Available Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots

  15. Using Machine Learning for Land Suitability Classification

    African Journals Online (AJOL)

    User

    West African Journal of Applied Ecology, vol. ... evidence for the utility of machine learning methods in land suitability classification especially MCS methods. ... Artificial intelligence tools. ..... Numerical values of index for the various classes.

  16. Classification of soil respiration in areas of sugarcane renewal using decision tree

    Directory of Open Access Journals (Sweden)

    Camila Viana Vieira Farhate

    Full Text Available ABSTRACT: The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response variable. The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS, chisquare method (χ2 and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soil moisture > potential acidity.

  17. The Costs of Supervised Classification: The Effect of Learning Task on Conceptual Flexibility

    Science.gov (United States)

    Hoffman, Aaron B.; Rehder, Bob

    2010-01-01

    Research has shown that learning a concept via standard supervised classification leads to a focus on diagnostic features, whereas learning by inferring missing features promotes the acquisition of within-category information. Accordingly, we predicted that classification learning would produce a deficit in people's ability to draw "novel…

  18. An Improved Brain-Inspired Emotional Learning Algorithm for Fast Classification

    Directory of Open Access Journals (Sweden)

    Ying Mei

    2017-06-01

    Full Text Available Classification is an important task of machine intelligence in the field of information. The artificial neural network (ANN is widely used for classification. However, the traditional ANN shows slow training speed, and it is hard to meet the real-time requirement for large-scale applications. In this paper, an improved brain-inspired emotional learning (BEL algorithm is proposed for fast classification. The BEL algorithm was put forward to mimic the high speed of the emotional learning mechanism in mammalian brain, which has the superior features of fast learning and low computational complexity. To improve the accuracy of BEL in classification, the genetic algorithm (GA is adopted for optimally tuning the weights and biases of amygdala and orbitofrontal cortex in the BEL neural network. The combinational algorithm named as GA-BEL has been tested on eight University of California at Irvine (UCI datasets and two well-known databases (Japanese Female Facial Expression, Cohn–Kanade. The comparisons of experiments indicate that the proposed GA-BEL is more accurate than the original BEL algorithm, and it is much faster than the traditional algorithm.

  19. Manifold regularized multitask learning for semi-supervised multilabel image classification.

    Science.gov (United States)

    Luo, Yong; Tao, Dacheng; Geng, Bo; Xu, Chao; Maybank, Stephen J

    2013-02-01

    It is a significant challenge to classify images with multiple labels by using only a small number of labeled samples. One option is to learn a binary classifier for each label and use manifold regularization to improve the classification performance by exploring the underlying geometric structure of the data distribution. However, such an approach does not perform well in practice when images from multiple concepts are represented by high-dimensional visual features. Thus, manifold regularization is insufficient to control the model complexity. In this paper, we propose a manifold regularized multitask learning (MRMTL) algorithm. MRMTL learns a discriminative subspace shared by multiple classification tasks by exploiting the common structure of these tasks. It effectively controls the model complexity because different tasks limit one another's search volume, and the manifold regularization ensures that the functions in the shared hypothesis space are smooth along the data manifold. We conduct extensive experiments, on the PASCAL VOC'07 dataset with 20 classes and the MIR dataset with 38 classes, by comparing MRMTL with popular image classification algorithms. The results suggest that MRMTL is effective for image classification.

  20. A Decision-Tree-Based Algorithm for Speech/Music Classification and Segmentation

    Directory of Open Access Journals (Sweden)

    Lavner Yizhar

    2009-01-01

    Full Text Available We present an efficient algorithm for segmentation of audio signals into speech or music. The central motivation to our study is consumer audio applications, where various real-time enhancements are often applied. The algorithm consists of a learning phase and a classification phase. In the learning phase, predefined training data is used for computing various time-domain and frequency-domain features, for speech and music signals separately, and estimating the optimal speech/music thresholds, based on the probability density functions of the features. An automatic procedure is employed to select the best features for separation. In the test phase, initial classification is performed for each segment of the audio signal, using a three-stage sieve-like approach, applying both Bayesian and rule-based methods. To avoid erroneous rapid alternations in the classification, a smoothing technique is applied, averaging the decision on each segment with past segment decisions. Extensive evaluation of the algorithm, on a database of more than 12 hours of speech and more than 22 hours of music showed correct identification rates of 99.4% and 97.8%, respectively, and quick adjustment to alternating speech/music sections. In addition to its accuracy and robustness, the algorithm can be easily adapted to different audio types, and is suitable for real-time operation.

  1. Joint Concept Correlation and Feature-Concept Relevance Learning for Multilabel Classification.

    Science.gov (United States)

    Zhao, Xiaowei; Ma, Zhigang; Li, Zhi; Li, Zhihui

    2018-02-01

    In recent years, multilabel classification has attracted significant attention in multimedia annotation. However, most of the multilabel classification methods focus only on the inherent correlations existing among multiple labels and concepts and ignore the relevance between features and the target concepts. To obtain more robust multilabel classification results, we propose a new multilabel classification method aiming to capture the correlations among multiple concepts by leveraging hypergraph that is proved to be beneficial for relational learning. Moreover, we consider mining feature-concept relevance, which is often overlooked by many multilabel learning algorithms. To better show the feature-concept relevance, we impose a sparsity constraint on the proposed method. We compare the proposed method with several other multilabel classification methods and evaluate the classification performance by mean average precision on several data sets. The experimental results show that the proposed method outperforms the state-of-the-art methods.

  2. Large-Scale Machine Learning for Classification and Search

    Science.gov (United States)

    Liu, Wei

    2012-01-01

    With the rapid development of the Internet, nowadays tremendous amounts of data including images and videos, up to millions or billions, can be collected for training machine learning models. Inspired by this trend, this thesis is dedicated to developing large-scale machine learning techniques for the purpose of making classification and nearest…

  3. EEG Eye State Identification Using Incremental Attribute Learning with Time-Series Classification

    Directory of Open Access Journals (Sweden)

    Ting Wang

    2014-01-01

    Full Text Available Eye state identification is a kind of common time-series classification problem which is also a hot spot in recent research. Electroencephalography (EEG is widely used in eye state classification to detect human's cognition state. Previous research has validated the feasibility of machine learning and statistical approaches for EEG eye state classification. This paper aims to propose a novel approach for EEG eye state identification using incremental attribute learning (IAL based on neural networks. IAL is a novel machine learning strategy which gradually imports and trains features one by one. Previous studies have verified that such an approach is applicable for solving a number of pattern recognition problems. However, in these previous works, little research on IAL focused on its application to time-series problems. Therefore, it is still unknown whether IAL can be employed to cope with time-series problems like EEG eye state classification. Experimental results in this study demonstrates that, with proper feature extraction and feature ordering, IAL can not only efficiently cope with time-series classification problems, but also exhibit better classification performance in terms of classification error rates in comparison with conventional and some other approaches.

  4. A Classification Framework Applied to Cancer Gene Expression Profiles

    Directory of Open Access Journals (Sweden)

    Hussein Hijazi

    2013-01-01

    Full Text Available Classification of cancer based on gene expression has provided insight into possible treatment strategies. Thus, developing machine learning methods that can successfully distinguish among cancer subtypes or normal versus cancer samples is important. This work discusses supervised learning techniques that have been employed to classify cancers. Furthermore, a two-step feature selection method based on an attribute estimation method (e.g., ReliefF and a genetic algorithm was employed to find a set of genes that can best differentiate between cancer subtypes or normal versus cancer samples. The application of different classification methods (e.g., decision tree, k-nearest neighbor, support vector machine (SVM, bagging, and random forest on 5 cancer datasets shows that no classification method universally outperforms all the others. However, k-nearest neighbor and linear SVM generally improve the classification performance over other classifiers. Finally, incorporating diverse types of genomic data (e.g., protein-protein interaction data and gene expression increase the prediction accuracy as compared to using gene expression alone.

  5. CLASS-PAIR-GUIDED MULTIPLE KERNEL LEARNING OF INTEGRATING HETEROGENEOUS FEATURES FOR CLASSIFICATION

    Directory of Open Access Journals (Sweden)

    Q. Wang

    2017-10-01

    Full Text Available In recent years, many studies on remote sensing image classification have shown that using multiple features from different data sources can effectively improve the classification accuracy. As a very powerful means of learning, multiple kernel learning (MKL can conveniently be embedded in a variety of characteristics. The conventional combined kernel learned by MKL can be regarded as the compromise of all basic kernels for all classes in classification. It is the best of the whole, but not optimal for each specific class. For this problem, this paper proposes a class-pair-guided MKL method to integrate the heterogeneous features (HFs from multispectral image (MSI and light detection and ranging (LiDAR data. In particular, the one-against-one strategy is adopted, which converts multiclass classification problem to a plurality of two-class classification problem. Then, we select the best kernel from pre-constructed basic kernels set for each class-pair by kernel alignment (KA in the process of classification. The advantage of the proposed method is that only the best kernel for the classification of any two classes can be retained, which leads to greatly enhanced discriminability. Experiments are conducted on two real data sets, and the experimental results show that the proposed method achieves the best performance in terms of classification accuracies in integrating the HFs for classification when compared with several state-of-the-art algorithms.

  6. Identification of pests and diseases of Dalbergia hainanensis based on EVI time series and classification of decision tree

    Science.gov (United States)

    Luo, Qiu; Xin, Wu; Qiming, Xiong

    2017-06-01

    In the process of vegetation remote sensing information extraction, the problem of phenological features and low performance of remote sensing analysis algorithm is not considered. To solve this problem, the method of remote sensing vegetation information based on EVI time-series and the classification of decision-tree of multi-source branch similarity is promoted. Firstly, to improve the time-series stability of recognition accuracy, the seasonal feature of vegetation is extracted based on the fitting span range of time-series. Secondly, the decision-tree similarity is distinguished by adaptive selection path or probability parameter of component prediction. As an index, it is to evaluate the degree of task association, decide whether to perform migration of multi-source decision tree, and ensure the speed of migration. Finally, the accuracy of classification and recognition of pests and diseases can reach 87%--98% of commercial forest in Dalbergia hainanensis, which is significantly better than that of MODIS coverage accuracy of 80%--96% in this area. Therefore, the validity of the proposed method can be verified.

  7. Automated morphological analysis of bone marrow cells in microscopic images for diagnosis of leukemia: nucleus-plasma separation and cell classification using a hierarchical tree model of hematopoesis

    Science.gov (United States)

    Krappe, Sebastian; Wittenberg, Thomas; Haferlach, Torsten; Münzenmayer, Christian

    2016-03-01

    The morphological differentiation of bone marrow is fundamental for the diagnosis of leukemia. Currently, the counting and classification of the different types of bone marrow cells is done manually under the use of bright field microscopy. This is a time-consuming, subjective, tedious and error-prone process. Furthermore, repeated examinations of a slide may yield intra- and inter-observer variances. For that reason a computer assisted diagnosis system for bone marrow differentiation is pursued. In this work we focus (a) on a new method for the separation of nucleus and plasma parts and (b) on a knowledge-based hierarchical tree classifier for the differentiation of bone marrow cells in 16 different classes. Classification trees are easily interpretable and understandable and provide a classification together with an explanation. Using classification trees, expert knowledge (i.e. knowledge about similar classes and cell lines in the tree model of hematopoiesis) is integrated in the structure of the tree. The proposed segmentation method is evaluated with more than 10,000 manually segmented cells. For the evaluation of the proposed hierarchical classifier more than 140,000 automatically segmented bone marrow cells are used. Future automated solutions for the morphological analysis of bone marrow smears could potentially apply such an approach for the pre-classification of bone marrow cells and thereby shortening the examination time.

  8. E-LEARNING TOOLS: STRUCTURE, CONTENT, CLASSIFICATION

    Directory of Open Access Journals (Sweden)

    Yuliya H. Loboda

    2012-05-01

    Full Text Available The article analyses the problems of organization of educational process with use of electronic means of education. Specifies the definition of "electronic learning", their structure and content. Didactic principles are considered, which are the basis of their creation and use. Given the detailed characteristics of e-learning tools for methodological purposes. On the basis of the allocated pedagogical problems of the use of electronic means of education presented and complemented by their classification, namely the means of theoretical and technological training, means of practical training, support tools, and comprehensive facilities.

  9. Using the PDD Behavior Inventory as a Level 2 Screener: A Classification and Regression Trees Analysis

    Science.gov (United States)

    Cohen, Ira L.; Liu, Xudong; Hudson, Melissa; Gillis, Jennifer; Cavalari, Rachel N. S.; Romanczyk, Raymond G.; Karmel, Bernard Z.; Gardner, Judith M.

    2016-01-01

    In order to improve discrimination accuracy between Autism Spectrum Disorder (ASD) and similar neurodevelopmental disorders, a data mining procedure, Classification and Regression Trees (CART), was used on a large multi-site sample of PDD Behavior Inventory (PDDBI) forms on children with and without ASD. Discrimination accuracy exceeded 80%,…

  10. Quantum learning: asymptotically optimal classification of qubit states

    International Nuclear Information System (INIS)

    Guta, Madalin; Kotlowski, Wojciech

    2010-01-01

    Pattern recognition is a central topic in learning theory, with numerous applications such as voice and text recognition, image analysis and computer diagnosis. The statistical setup in classification is the following: we are given an i.i.d. training set (X 1 , Y 1 ), ... , (X n , Y n ), where X i represents a feature and Y i in{0, 1} is a label attached to that feature. The underlying joint distribution of (X, Y) is unknown, but we can learn about it from the training set, and we aim at devising low error classifiers f: X→Y used to predict the label of new incoming features. In this paper, we solve a quantum analogue of this problem, namely the classification of two arbitrary unknown mixed qubit states. Given a number of 'training' copies from each of the states, we would like to 'learn' about them by performing a measurement on the training set. The outcome is then used to design measurements for the classification of future systems with unknown labels. We found the asymptotically optimal classification strategy and show that typically it performs strictly better than a plug-in strategy, which consists of estimating the states separately and then discriminating between them using the Helstrom measurement. The figure of merit is given by the excess risk equal to the difference between the probability of error and the probability of error of the optimal measurement for known states. We show that the excess risk scales as n -1 and compute the exact constant of the rate.

  11. Fusion of LiDAR and aerial imagery for the estimation of downed tree volume using Support Vector Machines classification and region based object fitting

    Science.gov (United States)

    Selvarajan, Sowmya

    The study classifies 3D small footprint full waveform digitized LiDAR fused with aerial imagery to downed trees using Support Vector Machines (SVM) algorithm. Using small footprint waveform LiDAR, airborne LiDAR systems can provide better canopy penetration and very high spatial resolution. The small footprint waveform scanner system Riegl LMS-Q680 is addition with an UltraCamX aerial camera are used to measure and map downed trees in a forest. The various data preprocessing steps helped in the identification of ground points from the dense LiDAR dataset and segment the LiDAR data to help reduce the complexity of the algorithm. The haze filtering process helped to differentiate the spectral signatures of the various classes within the aerial image. Such processes, helped to better select the features from both sensor data. The six features: LiDAR height, LiDAR intensity, LiDAR echo, and three image intensities are utilized. To do so, LiDAR derived, aerial image derived and fused LiDAR-aerial image derived features are used to organize the data for the SVM hypothesis formulation. Several variations of the SVM algorithm with different kernels and soft margin parameter C are experimented. The algorithm is implemented to classify downed trees over a pine trees zone. The LiDAR derived features provided an overall accuracy of 98% of downed trees but with no classification error of 86%. The image derived features provided an overall accuracy of 65% and fusion derived features resulted in an overall accuracy of 88%. The results are observed to be stable and robust. The SVM accuracies were accompanied by high false alarm rates, with the LiDAR classification producing 58.45%, image classification producing 95.74% and finally the fused classification producing 93% false alarm rates The Canny edge correction filter helped control the LiDAR false alarm to 35.99%, image false alarm to 48.56% and fused false alarm to 37.69% The implemented classifiers provided a powerful tool for

  12. Out-of-Sample Generalizations for Supervised Manifold Learning for Classification.

    Science.gov (United States)

    Vural, Elif; Guillemot, Christine

    2016-03-01

    Supervised manifold learning methods for data classification map high-dimensional data samples to a lower dimensional domain in a structure-preserving way while increasing the separation between different classes. Most manifold learning methods compute the embedding only of the initially available data; however, the generalization of the embedding to novel points, i.e., the out-of-sample extension problem, becomes especially important in classification applications. In this paper, we propose a semi-supervised method for building an interpolation function that provides an out-of-sample extension for general supervised manifold learning algorithms studied in the context of classification. The proposed algorithm computes a radial basis function interpolator that minimizes an objective function consisting of the total embedding error of unlabeled test samples, defined as their distance to the embeddings of the manifolds of their own class, as well as a regularization term that controls the smoothness of the interpolation function in a direction-dependent way. The class labels of test data and the interpolation function parameters are estimated jointly with an iterative process. Experimental results on face and object images demonstrate the potential of the proposed out-of-sample extension algorithm for the classification of manifold-modeled data sets.

  13. Machine learning algorithms for mode-of-action classification in toxicity assessment.

    Science.gov (United States)

    Zhang, Yile; Wong, Yau Shu; Deng, Jian; Anton, Cristina; Gabos, Stephan; Zhang, Weiping; Huang, Dorothy Yu; Jin, Can

    2016-01-01

    Real Time Cell Analysis (RTCA) technology is used to monitor cellular changes continuously over the entire exposure period. Combining with different testing concentrations, the profiles have potential in probing the mode of action (MOA) of the testing substances. In this paper, we present machine learning approaches for MOA assessment. Computational tools based on artificial neural network (ANN) and support vector machine (SVM) are developed to analyze the time-concentration response curves (TCRCs) of human cell lines responding to tested chemicals. The techniques are capable of learning data from given TCRCs with known MOA information and then making MOA classification for the unknown toxicity. A novel data processing step based on wavelet transform is introduced to extract important features from the original TCRC data. From the dose response curves, time interval leading to higher classification success rate can be selected as input to enhance the performance of the machine learning algorithm. This is particularly helpful when handling cases with limited and imbalanced data. The validation of the proposed method is demonstrated by the supervised learning algorithm applied to the exposure data of HepG2 cell line to 63 chemicals with 11 concentrations in each test case. Classification success rate in the range of 85 to 95 % are obtained using SVM for MOA classification with two clusters to cases up to four clusters. Wavelet transform is capable of capturing important features of TCRCs for MOA classification. The proposed SVM scheme incorporated with wavelet transform has a great potential for large scale MOA classification and high-through output chemical screening.

  14. Mastectomy or breast conserving surgery? Factors affecting type of surgical treatment for breast cancer – a classification tree approach

    International Nuclear Information System (INIS)

    Martin, Michael A; Meyricke, Ramona; O'Neill, Terry; Roberts, Steven

    2006-01-01

    A critical choice facing breast cancer patients is which surgical treatment – mastectomy or breast conserving surgery (BCS) – is most appropriate. Several studies have investigated factors that impact the type of surgery chosen, identifying features such as place of residence, age at diagnosis, tumor size, socio-economic and racial/ethnic elements as relevant. Such assessment of 'propensity' is important in understanding issues such as a reported under-utilisation of BCS among women for whom such treatment was not contraindicated. Using Western Australian (WA) data, we further examine the factors associated with the type of surgical treatment for breast cancer using a classification tree approach. This approach deals naturally with complicated interactions between factors, and so allows flexible and interpretable models for treatment choice to be built that add to the current understanding of this complex decision process. Data was extracted from the WA Cancer Registry on women diagnosed with breast cancer in WA from 1990 to 2000. Subjects' treatment preferences were predicted from covariates using both classification trees and logistic regression. Tumor size was the primary determinant of patient choice, subjects with tumors smaller than 20 mm in diameter preferring BCS. For subjects with tumors greater than 20 mm in diameter factors such as patient age, nodal status, and tumor histology become relevant as predictors of patient choice. Classification trees perform as well as logistic regression for predicting patient choice, but are much easier to interpret for clinical use. The selected tree can inform clinicians' advice to patients

  15. An Ontology to Support the Classification of Learning Material in an Organizational Learning Environment: An Evaluation

    Science.gov (United States)

    Valaski, Joselaine; Reinehr, Sheila; Malucelli, Andreia

    2017-01-01

    Purpose: The purpose of this research was to evaluate whether ontology integrated in an organizational learning environment may support the automatic learning material classification in a specific knowledge area. Design/methodology/approach: An ontology for recommending learning material was integrated in the organizational learning environment…

  16. Deep learning application: rubbish classification with aid of an android device

    Science.gov (United States)

    Liu, Sijiang; Jiang, Bo; Zhan, Jie

    2017-06-01

    Deep learning is a very hot topic currently in pattern recognition and artificial intelligence researches. Aiming at the practical problem that people usually don't know correct classifications some rubbish should belong to, based on the powerful image classification ability of the deep learning method, we have designed a prototype system to help users to classify kinds of rubbish. Firstly the CaffeNet Model was adopted for our classification network training on the ImageNet dataset, and the trained network was deployed on a web server. Secondly an android app was developed for users to capture images of unclassified rubbish, upload images to the web server for analyzing backstage and retrieve the feedback, so that users can obtain the classification guide by an android device conveniently. Tests on our prototype system of rubbish classification show that: an image of one single type of rubbish with origin shape can be better used to judge its classification, while an image containing kinds of rubbish or rubbish with changed shape may fail to help users to decide rubbish's classification. However, the system still shows promising auxiliary function for rubbish classification if the network training strategy can be optimized further.

  17. Learning from examples - Generation and evaluation of decision trees for software resource analysis

    Science.gov (United States)

    Selby, Richard W.; Porter, Adam A.

    1988-01-01

    A general solution method for the automatic generation of decision (or classification) trees is investigated. The approach is to provide insights through in-depth empirical characterization and evaluation of decision trees for software resource data analysis. The trees identify classes of objects (software modules) that had high development effort. Sixteen software systems ranging from 3,000 to 112,000 source lines were selected for analysis from a NASA production environment. The collection and analysis of 74 attributes (or metrics), for over 4,700 objects, captured information about the development effort, faults, changes, design style, and implementation style. A total of 9,600 decision trees were automatically generated and evaluated. The trees correctly identified 79.3 percent of the software modules that had high development effort or faults, and the trees generated from the best parameter combinations correctly identified 88.4 percent of the modules on the average.

  18. Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

    Science.gov (United States)

    Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

    2016-01-01

    Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

  19. Runtime Optimizations for Tree-Based Machine Learning Models

    NARCIS (Netherlands)

    N. Asadi; J.J.P. Lin (Jimmy); A.P. de Vries (Arjen)

    2014-01-01

    htmlabstractTree-based models have proven to be an effective solution for web ranking as well as other machine learning problems in diverse domains. This paper focuses on optimizing the runtime performance of applying such models to make predictions, specifically using gradient-boosted regression

  20. Classification Framework for ICT-Based Learning Technologies for Disabled People

    Science.gov (United States)

    Hersh, Marion

    2017-01-01

    The paper presents the first systematic approach to the classification of inclusive information and communication technologies (ICT)-based learning technologies and ICT-based learning technologies for disabled people which covers both assistive and general learning technologies, is valid for all disabled people and considers the full range of…

  1. Feasibility of Machine Learning Methods for Separating Wood and Leaf Points from Terrestrial Laser Scanning Data

    Science.gov (United States)

    Wang, D.; Hollaus, M.; Pfeifer, N.

    2017-09-01

    Classification of wood and leaf components of trees is an essential prerequisite for deriving vital tree attributes, such as wood mass, leaf area index (LAI) and woody-to-total area. Laser scanning emerges to be a promising solution for such a request. Intensity based approaches are widely proposed, as different components of a tree can feature discriminatory optical properties at the operating wavelengths of a sensor system. For geometry based methods, machine learning algorithms are often used to separate wood and leaf points, by providing proper training samples. However, it remains unclear how the chosen machine learning classifier and features used would influence classification results. To this purpose, we compare four popular machine learning classifiers, namely Support Vector Machine (SVM), Na¨ıve Bayes (NB), Random Forest (RF), and Gaussian Mixture Model (GMM), for separating wood and leaf points from terrestrial laser scanning (TLS) data. Two trees, an Erytrophleum fordii and a Betula pendula (silver birch) are used to test the impacts from classifier, feature set, and training samples. Our results showed that RF is the best model in terms of accuracy, and local density related features are important. Experimental results confirmed the feasibility of machine learning algorithms for the reliable classification of wood and leaf points. It is also noted that our studies are based on isolated trees. Further tests should be performed on more tree species and data from more complex environments.

  2. FEASIBILITY OF MACHINE LEARNING METHODS FOR SEPARATING WOOD AND LEAF POINTS FROM TERRESTRIAL LASER SCANNING DATA

    Directory of Open Access Journals (Sweden)

    D. Wang

    2017-09-01

    Full Text Available Classification of wood and leaf components of trees is an essential prerequisite for deriving vital tree attributes, such as wood mass, leaf area index (LAI and woody-to-total area. Laser scanning emerges to be a promising solution for such a request. Intensity based approaches are widely proposed, as different components of a tree can feature discriminatory optical properties at the operating wavelengths of a sensor system. For geometry based methods, machine learning algorithms are often used to separate wood and leaf points, by providing proper training samples. However, it remains unclear how the chosen machine learning classifier and features used would influence classification results. To this purpose, we compare four popular machine learning classifiers, namely Support Vector Machine (SVM, Na¨ıve Bayes (NB, Random Forest (RF, and Gaussian Mixture Model (GMM, for separating wood and leaf points from terrestrial laser scanning (TLS data. Two trees, an Erytrophleum fordii and a Betula pendula (silver birch are used to test the impacts from classifier, feature set, and training samples. Our results showed that RF is the best model in terms of accuracy, and local density related features are important. Experimental results confirmed the feasibility of machine learning algorithms for the reliable classification of wood and leaf points. It is also noted that our studies are based on isolated trees. Further tests should be performed on more tree species and data from more complex environments.

  3. First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe

    Directory of Open Access Journals (Sweden)

    Markus Immitzer

    2016-02-01

    Full Text Available The study presents the preliminary results of two classification exercises assessing the capabilities of pre-operational (August 2015 Sentinel-2 (S2 data for mapping crop types and tree species. In the first case study, an S2 image was used to map six summer crop species in Lower Austria as well as winter crops/bare soil. Crop type maps are needed to account for crop-specific water use and for agricultural statistics. Crop type information is also useful to parametrize crop growth models for yield estimation, as well as for the retrieval of vegetation biophysical variables using radiative transfer models. The second case study aimed to map seven different deciduous and coniferous tree species in Germany. Detailed information about tree species distribution is important for forest management and to assess potential impacts of climate change. In our S2 data assessment, crop and tree species maps were produced at 10 m spatial resolution by combining the ten S2 spectral channels with 10 and 20 m pixel size. A supervised Random Forest classifier (RF was deployed and trained with appropriate ground truth. In both case studies, S2 data confirmed its expected capabilities to produce reliable land cover maps. Cross-validated overall accuracies ranged between 65% (tree species and 76% (crop types. The study confirmed the high value of the red-edge and shortwave infrared (SWIR bands for vegetation mapping. Also, the blue band was important in both study sites. The S2-bands in the near infrared were amongst the least important channels. The object based image analysis (OBIA and the classical pixel-based classification achieved comparable results, mainly for the cropland. As only single date acquisitions were available for this study, the full potential of S2 data could not be assessed. In the future, the two twin S2 satellites will offer global coverage every five days and therefore permit to concurrently exploit unprecedented spectral and temporal

  4. Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree

    KAUST Repository

    Zheng, Yuhan

    2018-05-07

    Remote sensing is the main approach used to classify and map aquatic vegetation, and classification tree (CT) analysis is superior to various classification methods. Based on previous studies, modified CT can be developed from traditional CT by adjusting the thresholds based on the statistical relationship between spectral features to classify different images without ground-truth data. However, no studies have yet employed this method to resolve marine vegetation. In this study, three Gao-Fen 1 satellite images obtained with the same sensor on January 30, 2014, November 5, 2014, and January 21, 2015 were selected, and two features were then employed to extract macroalgae from aquaculture farms from the seawater background. Besides, object-based classification and other image analysis methods were adopted to improve the classification accuracy in this study. Results show that the overall accuracies of traditional CTs for three images are 92.0%, 94.2% and 93.9%, respectively, whereas the overall accuracies of the two corresponding modified CTs for images obtained on January 21, 2015 and November 5, 2014 are 93.1% and 89.5%, respectively. This indicates modified CTs can help map macroalgae with multi-date imagery and monitor the spatiotemporal distribution of macroalgae in coastal environments.

  5. Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree

    KAUST Repository

    Zheng, Yuhan; Duarte, Carlos M.; Chen, Jiang; Li, Dan; Lou, Zhaohan; Wu, Jiaping

    2018-01-01

    Remote sensing is the main approach used to classify and map aquatic vegetation, and classification tree (CT) analysis is superior to various classification methods. Based on previous studies, modified CT can be developed from traditional CT by adjusting the thresholds based on the statistical relationship between spectral features to classify different images without ground-truth data. However, no studies have yet employed this method to resolve marine vegetation. In this study, three Gao-Fen 1 satellite images obtained with the same sensor on January 30, 2014, November 5, 2014, and January 21, 2015 were selected, and two features were then employed to extract macroalgae from aquaculture farms from the seawater background. Besides, object-based classification and other image analysis methods were adopted to improve the classification accuracy in this study. Results show that the overall accuracies of traditional CTs for three images are 92.0%, 94.2% and 93.9%, respectively, whereas the overall accuracies of the two corresponding modified CTs for images obtained on January 21, 2015 and November 5, 2014 are 93.1% and 89.5%, respectively. This indicates modified CTs can help map macroalgae with multi-date imagery and monitor the spatiotemporal distribution of macroalgae in coastal environments.

  6. Supervised Learning for Visual Pattern Classification

    Science.gov (United States)

    Zheng, Nanning; Xue, Jianru

    This chapter presents an overview of the topics and major ideas of supervised learning for visual pattern classification. Two prevalent algorithms, i.e., the support vector machine (SVM) and the boosting algorithm, are briefly introduced. SVMs and boosting algorithms are two hot topics of recent research in supervised learning. SVMs improve the generalization of the learning machine by implementing the rule of structural risk minimization (SRM). It exhibits good generalization even when little training data are available for machine training. The boosting algorithm can boost a weak classifier to a strong classifier by means of the so-called classifier combination. This algorithm provides a general way for producing a classifier with high generalization capability from a great number of weak classifiers.

  7. Effects of sample survey design on the accuracy of classification tree models in species distribution models

    Science.gov (United States)

    Thomas C. Edwards; D. Richard Cutler; Niklaus E. Zimmermann; Linda Geiser; Gretchen G. Moisen

    2006-01-01

    We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by...

  8. Preventing KPI Violations in Business Processes based on Decision Tree Learning and Proactive Runtime Adaptation

    Directory of Open Access Journals (Sweden)

    Dimka Karastoyanova

    2012-01-01

    Full Text Available The performance of business processes is measured and monitored in terms of Key Performance Indicators (KPIs. If the monitoring results show that the KPI targets are violated, the underlying reasons have to be identified and the process should be adapted accordingly to address the violations. In this paper we propose an integrated monitoring, prediction and adaptation approach for preventing KPI violations of business process instances. KPIs are monitored continuously while the process is executed. Additionally, based on KPI measurements of historical process instances we use decision tree learning to construct classification models which are then used to predict the KPI value of an instance while it is still running. If a KPI violation is predicted, we identify adaptation requirements and adaptation strategies in order to prevent the violation.

  9. Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System.

    Science.gov (United States)

    Jiang, Yizhang; Wu, Dongrui; Deng, Zhaohong; Qian, Pengjiang; Wang, Jun; Wang, Guanjin; Chung, Fu-Lai; Choi, Kup-Sze; Wang, Shitong

    2017-12-01

    Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy. Compared with manual labeling of EEG signals by doctors, machine learning approaches can be faster and more consistent. However, the classification accuracy is usually not satisfactory for two main reasons: the distributions of the data used for training and testing may be different, and the amount of training data may not be enough. In addition, most machine learning approaches generate black-box models that are difficult to interpret. In this paper, we integrate transductive transfer learning, semi-supervised learning and TSK fuzzy system to tackle these three problems. More specifically, we use transfer learning to reduce the discrepancy in data distribution between the training and testing data, employ semi-supervised learning to use the unlabeled testing data to remedy the shortage of training data, and adopt TSK fuzzy system to increase model interpretability. Two learning algorithms are proposed to train the system. Our experimental results show that the proposed approaches can achieve better performance than many state-of-the-art seizure classification algorithms.

  10. Decision-Tree, Rule-Based, and Random Forest Classification of High-Resolution Multispectral Imagery for Wetland Mapping and Inventory

    Science.gov (United States)

    Efforts are increasingly being made to classify the world’s wetland resources, an important ecosystem and habitat that is diminishing in abundance. There are multiple remote sensing classification methods, including a suite of nonparametric classifiers such as decision-tree...

  11. Identification of Sexually Abused Female Adolescents at Risk for Suicidal Ideations: A Classification and Regression Tree Analysis

    Science.gov (United States)

    Brabant, Marie-Eve; Hebert, Martine; Chagnon, Francois

    2013-01-01

    This study explored the clinical profiles of 77 female teenager survivors of sexual abuse and examined the association of abuse-related and personal variables with suicidal ideations. Analyses revealed that 64% of participants experienced suicidal ideations. Findings from classification and regression tree analysis indicated that depression,…

  12. Malignancy Risk Assessment in Patients with Thyroid Nodules Using Classification and Regression Trees

    Directory of Open Access Journals (Sweden)

    Shokouh Taghipour Zahir

    2013-01-01

    Full Text Available Purpose. We sought to investigate the utility of classification and regression trees (CART classifier to differentiate benign from malignant nodules in patients referred for thyroid surgery. Methods. Clinical and demographic data of 271 patients referred to the Sadoughi Hospital during 2006–2011 were collected. In a two-step approach, a CART classifier was employed to differentiate patients with a high versus low risk of thyroid malignancy. The first step served as the screening procedure and was tailored to produce as few false negatives as possible. The second step identified those with the lowest risk of malignancy, chosen from a high risk population. Sensitivity, specificity, positive and negative predictive values (PPV and NPV of the optimal tree were calculated. Results. In the first step, age, sex, and nodule size contributed to the optimal tree. Ultrasonographic features were employed in the second step with hypoechogenicity and/or microcalcifications yielding the highest discriminatory ability. The combined tree produced a sensitivity and specificity of 80.0% (95% CI: 29.9–98.9 and 94.1% (95% CI: 78.9–99.0, respectively. NPV and PPV were 66.7% (41.1–85.6 and 97.0% (82.5–99.8, respectively. Conclusion. CART classifier reliably identifies patients with a low risk of malignancy who can avoid unnecessary surgery.

  13. Evaluation of Decision Trees for Cloud Detection from AVHRR Data

    Science.gov (United States)

    Shiffman, Smadar; Nemani, Ramakrishna

    2005-01-01

    Automated cloud detection and tracking is an important step in assessing changes in radiation budgets associated with global climate change via remote sensing. Data products based on satellite imagery are available to the scientific community for studying trends in the Earth's atmosphere. The data products include pixel-based cloud masks that assign cloud-cover classifications to pixels. Many cloud-mask algorithms have the form of decision trees. The decision trees employ sequential tests that scientists designed based on empirical astrophysics studies and simulations. Limitations of existing cloud masks restrict our ability to accurately track changes in cloud patterns over time. In a previous study we compared automatically learned decision trees to cloud masks included in Advanced Very High Resolution Radiometer (AVHRR) data products from the year 2000. In this paper we report the replication of the study for five-year data, and for a gold standard based on surface observations performed by scientists at weather stations in the British Islands. For our sample data, the accuracy of automatically learned decision trees was greater than the accuracy of the cloud masks p < 0.001.

  14. Do pre-trained deep learning models improve computer-aided classification of digital mammograms?

    Science.gov (United States)

    Aboutalib, Sarah S.; Mohamed, Aly A.; Zuley, Margarita L.; Berg, Wendie A.; Luo, Yahong; Wu, Shandong

    2018-02-01

    Digital mammography screening is an important exam for the early detection of breast cancer and reduction in mortality. False positives leading to high recall rates, however, results in unnecessary negative consequences to patients and health care systems. In order to better aid radiologists, computer-aided tools can be utilized to improve distinction between image classifications and thus potentially reduce false recalls. The emergence of deep learning has shown promising results in the area of biomedical imaging data analysis. This study aimed to investigate deep learning and transfer learning methods that can improve digital mammography classification performance. In particular, we evaluated the effect of pre-training deep learning models with other imaging datasets in order to boost classification performance on a digital mammography dataset. Two types of datasets were used for pre-training: (1) a digitized film mammography dataset, and (2) a very large non-medical imaging dataset. By using either of these datasets to pre-train the network initially, and then fine-tuning with the digital mammography dataset, we found an increase in overall classification performance in comparison to a model without pre-training, with the very large non-medical dataset performing the best in improving the classification accuracy.

  15. Advances in Patient Classification for Traditional Chinese Medicine: A Machine Learning Perspective

    Science.gov (United States)

    Zhao, Changbo; Li, Guo-Zheng; Wang, Chengjun; Niu, Jinling

    2015-01-01

    As a complementary and alternative medicine in medical field, traditional Chinese medicine (TCM) has drawn great attention in the domestic field and overseas. In practice, TCM provides a quite distinct methodology to patient diagnosis and treatment compared to western medicine (WM). Syndrome (ZHENG or pattern) is differentiated by a set of symptoms and signs examined from an individual by four main diagnostic methods: inspection, auscultation and olfaction, interrogation, and palpation which reflects the pathological and physiological changes of disease occurrence and development. Patient classification is to divide patients into several classes based on different criteria. In this paper, from the machine learning perspective, a survey on patient classification issue will be summarized on three major aspects of TCM: sign classification, syndrome differentiation, and disease classification. With the consideration of different diagnostic data analyzed by different computational methods, we present the overview for four subfields of TCM diagnosis, respectively. For each subfield, we design a rectangular reference list with applications in the horizontal direction and machine learning algorithms in the longitudinal direction. According to the current development of objective TCM diagnosis for patient classification, a discussion of the research issues around machine learning techniques with applications to TCM diagnosis is given to facilitate the further research for TCM patient classification. PMID:26246834

  16. Advances in Patient Classification for Traditional Chinese Medicine: A Machine Learning Perspective.

    Science.gov (United States)

    Zhao, Changbo; Li, Guo-Zheng; Wang, Chengjun; Niu, Jinling

    2015-01-01

    As a complementary and alternative medicine in medical field, traditional Chinese medicine (TCM) has drawn great attention in the domestic field and overseas. In practice, TCM provides a quite distinct methodology to patient diagnosis and treatment compared to western medicine (WM). Syndrome (ZHENG or pattern) is differentiated by a set of symptoms and signs examined from an individual by four main diagnostic methods: inspection, auscultation and olfaction, interrogation, and palpation which reflects the pathological and physiological changes of disease occurrence and development. Patient classification is to divide patients into several classes based on different criteria. In this paper, from the machine learning perspective, a survey on patient classification issue will be summarized on three major aspects of TCM: sign classification, syndrome differentiation, and disease classification. With the consideration of different diagnostic data analyzed by different computational methods, we present the overview for four subfields of TCM diagnosis, respectively. For each subfield, we design a rectangular reference list with applications in the horizontal direction and machine learning algorithms in the longitudinal direction. According to the current development of objective TCM diagnosis for patient classification, a discussion of the research issues around machine learning techniques with applications to TCM diagnosis is given to facilitate the further research for TCM patient classification.

  17. Utilising Tree-Based Ensemble Learning for Speaker Segmentation

    DEFF Research Database (Denmark)

    Abou-Zleikha, Mohamed; Tan, Zheng-Hua; Christensen, Mads Græsbøll

    2014-01-01

    In audio and speech processing, accurate detection of the changing points between multiple speakers in speech segments is an important stage for several applications such as speaker identification and tracking. Bayesian Information Criteria (BIC)-based approaches are the most traditionally used...... for a certain condition, the model becomes biased to the data used for training limiting the model’s generalisation ability. In this paper, we propose a BIC-based tuning-free approach for speaker segmentation through the use of ensemble-based learning. A forest of segmentation trees is constructed in which each...... tree is trained using a sampled version of the speech segment. During the tree construction process, a set of randomly selected points in the input sequence is examined as potential segmentation points. The point that yields the highest ΔBIC is chosen and the same process is repeated for the resultant...

  18. Failure diagnosis using deep belief learning based health state classification

    International Nuclear Information System (INIS)

    Tamilselvan, Prasanna; Wang, Pingfeng

    2013-01-01

    Effective health diagnosis provides multifarious benefits such as improved safety, improved reliability and reduced costs for operation and maintenance of complex engineered systems. This paper presents a novel multi-sensor health diagnosis method using deep belief network (DBN). DBN has recently become a popular approach in machine learning for its promised advantages such as fast inference and the ability to encode richer and higher order network structures. The DBN employs a hierarchical structure with multiple stacked restricted Boltzmann machines and works through a layer by layer successive learning process. The proposed multi-sensor health diagnosis methodology using DBN based state classification can be structured in three consecutive stages: first, defining health states and preprocessing sensory data for DBN training and testing; second, developing DBN based classification models for diagnosis of predefined health states; third, validating DBN classification models with testing sensory dataset. Health diagnosis using DBN based health state classification technique is compared with four existing diagnosis techniques. Benchmark classification problems and two engineering health diagnosis applications: aircraft engine health diagnosis and electric power transformer health diagnosis are employed to demonstrate the efficacy of the proposed approach

  19. A novel application of deep learning for single-lead ECG classification.

    Science.gov (United States)

    Mathews, Sherin M; Kambhamettu, Chandra; Barner, Kenneth E

    2018-06-04

    Detecting and classifying cardiac arrhythmias is critical to the diagnosis of patients with cardiac abnormalities. In this paper, a novel approach based on deep learning methodology is proposed for the classification of single-lead electrocardiogram (ECG) signals. We demonstrate the application of the Restricted Boltzmann Machine (RBM) and deep belief networks (DBN) for ECG classification following detection of ventricular and supraventricular heartbeats using single-lead ECG. The effectiveness of this proposed algorithm is illustrated using real ECG signals from the widely-used MIT-BIH database. Simulation results demonstrate that with a suitable choice of parameters, RBM and DBN can achieve high average recognition accuracies of ventricular ectopic beats (93.63%) and of supraventricular ectopic beats (95.57%) at a low sampling rate of 114 Hz. Experimental results indicate that classifiers built into this deep learning-based framework achieved state-of-the art performance models at lower sampling rates and simple features when compared to traditional methods. Further, employing features extracted at a sampling rate of 114 Hz when combined with deep learning provided enough discriminatory power for the classification task. This performance is comparable to that of traditional methods and uses a much lower sampling rate and simpler features. Thus, our proposed deep neural network algorithm demonstrates that deep learning-based methods offer accurate ECG classification and could potentially be extended to other physiological signal classifications, such as those in arterial blood pressure (ABP), nerve conduction (EMG), and heart rate variability (HRV) studies. Copyright © 2018. Published by Elsevier Ltd.

  20. Detecting Structural Metadata with Decision Trees and Transformation-Based Learning

    National Research Council Canada - National Science Library

    Kim, Joungbum; Schwarm, Sarah E; Ostendorf, Mari

    2004-01-01

    .... Specifically, combinations of decision trees and language models are used to predict sentence ends and interruption points and given these events transformation based learning is used to detect edit...

  1. Living Classrooms: Learning Guide for Famous & Historic Trees.

    Science.gov (United States)

    American Forest Foundation, Washington, DC.

    This guide provides information to create and care for a Famous and Historic Trees Living Classroom in which students learn American history and culture in the context of environmental change. The booklet contains 10 hands-on activities that emphasize observation, critical thinking, and teamwork. Worksheets and illustrations provide students with…

  2. Unsupervised Feature Learning for Heart Sounds Classification Using Autoencoder

    Science.gov (United States)

    Hu, Wei; Lv, Jiancheng; Liu, Dongbo; Chen, Yao

    2018-04-01

    Cardiovascular disease seriously threatens the health of many people. It is usually diagnosed during cardiac auscultation, which is a fast and efficient method of cardiovascular disease diagnosis. In recent years, deep learning approach using unsupervised learning has made significant breakthroughs in many fields. However, to our knowledge, deep learning has not yet been used for heart sound classification. In this paper, we first use the average Shannon energy to extract the envelope of the heart sounds, then find the highest point of S1 to extract the cardiac cycle. We convert the time-domain signals of the cardiac cycle into spectrograms and apply principal component analysis whitening to reduce the dimensionality of the spectrogram. Finally, we apply a two-layer autoencoder to extract the features of the spectrogram. The experimental results demonstrate that the features from the autoencoder are suitable for heart sound classification.

  3. Electronic Nose Odor Classification with Advanced Decision Tree Structures

    Directory of Open Access Journals (Sweden)

    S. Guney

    2013-09-01

    Full Text Available Electronic nose (e-nose is an electronic device which can measure chemical compounds in air and consequently classify different odors. In this paper, an e-nose device consisting of 8 different gas sensors was designed and constructed. Using this device, 104 different experiments involving 11 different odor classes (moth, angelica root, rose, mint, polis, lemon, rotten egg, egg, garlic, grass, and acetone were performed. The main contribution of this paper is the finding that using the chemical domain knowledge it is possible to train an accurate odor classification system. The domain knowledge about chemical compounds is represented by a decision tree whose nodes are composed of classifiers such as Support Vector Machines and k-Nearest Neighbor. The overall accuracy achieved with the proposed algorithm and the constructed e-nose device was 97.18 %. Training and testing data sets used in this paper are published online.

  4. Characterization of Escherichia coli isolates from different fecal sources by means of classification tree analysis of fatty acid methyl ester (FAME) profiles.

    Science.gov (United States)

    Seurinck, Sylvie; Deschepper, Ellen; Deboch, Bishaw; Verstraete, Willy; Siciliano, Steven

    2006-03-01

    Microbial source tracking (MST) methods need to be rapid, inexpensive and accurate. Unfortunately, many MST methods provide a wealth of information that is difficult to interpret by the regulators who use this information to make decisions. This paper describes the use of classification tree analysis to interpret the results of a MST method based on fatty acid methyl ester (FAME) profiles of Escherichia coli isolates, and to present results in a format readily interpretable by water quality managers. Raw sewage E. coli isolates and animal E. coli isolates from cow, dog, gull, and horse were isolated and their FAME profiles collected. Correct classification rates determined with leaveone-out cross-validation resulted in an overall low correct classification rate of 61%. A higher overall correct classification rate of 85% was obtained when the animal isolates were pooled together and compared to the raw sewage isolates. Bootstrap aggregation or adaptive resampling and combining of the FAME profile data increased correct classification rates substantially. Other MST methods may be better suited to differentiate between different fecal sources but classification tree analysis has enabled us to distinguish raw sewage from animal E. coli isolates, which previously had not been possible with other multivariate methods such as principal component analysis and cluster analysis.

  5. Supervised machine learning and active learning in classification of radiology reports.

    Science.gov (United States)

    Nguyen, Dung H M; Patrick, Jon D

    2014-01-01

    This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry. In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney). The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL. AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly. The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

  6. A deep learning pipeline for Indian dance style classification

    Science.gov (United States)

    Dewan, Swati; Agarwal, Shubham; Singh, Navjyoti

    2018-04-01

    In this paper, we address the problem of dance style classification to classify Indian dance or any dance in general. We propose a 3-step deep learning pipeline. First, we extract 14 essential joint locations of the dancer from each video frame, this helps us to derive any body region location within the frame, we use this in the second step which forms the main part of our pipeline. Here, we divide the dancer into regions of important motion in each video frame. We then extract patches centered at these regions. Main discriminative motion is captured in these patches. We stack the features from all such patches of a frame into a single vector and form our hierarchical dance pose descriptor. Finally, in the third step, we build a high level representation of the dance video using the hierarchical descriptors and train it using a Recurrent Neural Network (RNN) for classification. Our novelty also lies in the way we use multiple representations for a single video. This helps us to: (1) Overcome the RNN limitation of learning small sequences over big sequences such as dance; (2) Extract more data from the available dataset for effective deep learning by training multiple representations. Our contributions in this paper are three-folds: (1) We provide a deep learning pipeline for classification of any form of dance; (2) We prove that a segmented representation of a dance video works well with sequence learning techniques for recognition purposes; (3) We extend and refine the ICD dataset and provide a new dataset for evaluation of dance. Our model performs comparable or better in some cases than the state-of-the-art on action recognition benchmarks.

  7. Discriminative Nonlinear Analysis Operator Learning: When Cosparse Model Meets Image Classification.

    Science.gov (United States)

    Wen, Zaidao; Hou, Biao; Jiao, Licheng

    2017-05-03

    Linear synthesis model based dictionary learning framework has achieved remarkable performances in image classification in the last decade. Behaved as a generative feature model, it however suffers from some intrinsic deficiencies. In this paper, we propose a novel parametric nonlinear analysis cosparse model (NACM) with which a unique feature vector will be much more efficiently extracted. Additionally, we derive a deep insight to demonstrate that NACM is capable of simultaneously learning the task adapted feature transformation and regularization to encode our preferences, domain prior knowledge and task oriented supervised information into the features. The proposed NACM is devoted to the classification task as a discriminative feature model and yield a novel discriminative nonlinear analysis operator learning framework (DNAOL). The theoretical analysis and experimental performances clearly demonstrate that DNAOL will not only achieve the better or at least competitive classification accuracies than the state-of-the-art algorithms but it can also dramatically reduce the time complexities in both training and testing phases.

  8. Convolutional neural network with transfer learning for rice type classification

    Science.gov (United States)

    Patel, Vaibhav Amit; Joshi, Manjunath V.

    2018-04-01

    Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

  9. CLASSIFICATION OF ENTREPRENEURIAL INTENTIONS BY NEURAL NETWORKS, DECISION TREES AND SUPPORT VECTOR MACHINES

    Directory of Open Access Journals (Sweden)

    Marijana Zekić-Sušac

    2010-12-01

    Full Text Available Entrepreneurial intentions of students are important to recognize during the study in order to provide those students with educational background that will support such intentions and lead them to successful entrepreneurship after the study. The paper aims to develop a model that will classify students according to their entrepreneurial intentions by benchmarking three machine learning classifiers: neural networks, decision trees, and support vector machines. A survey was conducted at a Croatian university including a sample of students at the first year of study. Input variables described students’ demographics, importance of business objectives, perception of entrepreneurial carrier, and entrepreneurial predispositions. Due to a large dimension of input space, a feature selection method was used in the pre-processing stage. For comparison reasons, all tested models were validated on the same out-of-sample dataset, and a cross-validation procedure for testing generalization ability of the models was conducted. The models were compared according to its classification accuracy, as well according to input variable importance. The results show that although the best neural network model produced the highest average hit rate, the difference in performance is not statistically significant. All three models also extract similar set of features relevant for classifying students, which can be suggested to be taken into consideration by universities while designing their academic programs.

  10. Phenotype classification of zebrafish embryos by supervised learning.

    Directory of Open Access Journals (Sweden)

    Nathalie Jeanray

    Full Text Available Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances on embryo survival and development are generally evaluated manually through microscopic observation by an expert and documented by several typical photographs. Here, we present a methodology to automatically classify brightfield images of wildtype zebrafish embryos according to their defects by using an image analysis approach based on supervised machine learning. We show that, compared to manual classification, automatic classification results in 90 to 100% agreement with consensus voting of biological experts in nine out of eleven considered defects in 3 days old zebrafish larvae. Automation of the analysis and classification of zebrafish embryo pictures reduces the workload and time required for the biological expert and increases the reproducibility and objectivity of this classification.

  11. Nonlinear programming for classification problems in machine learning

    Science.gov (United States)

    Astorino, Annabella; Fuduli, Antonio; Gaudioso, Manlio

    2016-10-01

    We survey some nonlinear models for classification problems arising in machine learning. In the last years this field has become more and more relevant due to a lot of practical applications, such as text and web classification, object recognition in machine vision, gene expression profile analysis, DNA and protein analysis, medical diagnosis, customer profiling etc. Classification deals with separation of sets by means of appropriate separation surfaces, which is generally obtained by solving a numerical optimization model. While linear separability is the basis of the most popular approach to classification, the Support Vector Machine (SVM), in the recent years using nonlinear separating surfaces has received some attention. The objective of this work is to recall some of such proposals, mainly in terms of the numerical optimization models. In particular we tackle the polyhedral, ellipsoidal, spherical and conical separation approaches and, for some of them, we also consider the semisupervised versions.

  12. A hybrid ensemble learning approach to star-galaxy classification

    Science.gov (United States)

    Kim, Edward J.; Brunner, Robert J.; Carrasco Kind, Matias

    2015-10-01

    There exist a variety of star-galaxy classification techniques, each with their own strengths and weaknesses. In this paper, we present a novel meta-classification framework that combines and fully exploits different techniques to produce a more robust star-galaxy classification. To demonstrate this hybrid, ensemble approach, we combine a purely morphological classifier, a supervised machine learning method based on random forest, an unsupervised machine learning method based on self-organizing maps, and a hierarchical Bayesian template-fitting method. Using data from the CFHTLenS survey (Canada-France-Hawaii Telescope Lensing Survey), we consider different scenarios: when a high-quality training set is available with spectroscopic labels from DEEP2 (Deep Extragalactic Evolutionary Probe Phase 2 ), SDSS (Sloan Digital Sky Survey), VIPERS (VIMOS Public Extragalactic Redshift Survey), and VVDS (VIMOS VLT Deep Survey), and when the demographics of sources in a low-quality training set do not match the demographics of objects in the test data set. We demonstrate that our Bayesian combination technique improves the overall performance over any individual classification method in these scenarios. Thus, strategies that combine the predictions of different classifiers may prove to be optimal in currently ongoing and forthcoming photometric surveys, such as the Dark Energy Survey and the Large Synoptic Survey Telescope.

  13. Tree Species Abundance Predictions in a Tropical Agricultural Landscape with a Supervised Classification Model and Imbalanced Data

    Directory of Open Access Journals (Sweden)

    Sarah J. Graves

    2016-02-01

    Full Text Available Mapping species through classification of imaging spectroscopy data is facilitating research to understand tree species distributions at increasingly greater spatial scales. Classification requires a dataset of field observations matched to the image, which will often reflect natural species distributions, resulting in an imbalanced dataset with many samples for common species and few samples for less common species. Despite the high prevalence of imbalanced datasets in multiclass species predictions, the effect on species prediction accuracy and landscape species abundance has not yet been quantified. First, we trained and assessed the accuracy of a support vector machine (SVM model with a highly imbalanced dataset of 20 tropical species and one mixed-species class of 24 species identified in a hyperspectral image mosaic (350–2500 nm of Panamanian farmland and secondary forest fragments. The model, with an overall accuracy of 62% ± 2.3% and F-score of 59% ± 2.7%, was applied to the full image mosaic (23,000 ha at a 2-m resolution to produce a species prediction map, which suggested that this tropical agricultural landscape is more diverse than what has been presented in field-based studies. Second, we quantified the effect of class imbalance on model accuracy. Model assessment showed a trend where species with more samples were consistently over predicted while species with fewer samples were under predicted. Standardizing sample size reduced model accuracy, but also reduced the level of species over- and under-prediction. This study advances operational species mapping of diverse tropical landscapes by detailing the effect of imbalanced data on classification accuracy and providing estimates of tree species abundance in an agricultural landscape. Species maps using data and methods presented here can be used in landscape analyses of species distributions to understand human or environmental effects, in addition to focusing conservation

  14. Use of Binary Partition Tree and energy minimization for object-based classification of urban land cover

    Science.gov (United States)

    Li, Mengmeng; Bijker, Wietske; Stein, Alfred

    2015-04-01

    Two main challenges are faced when classifying urban land cover from very high resolution satellite images: obtaining an optimal image segmentation and distinguishing buildings from other man-made objects. For optimal segmentation, this work proposes a hierarchical representation of an image by means of a Binary Partition Tree (BPT) and an unsupervised evaluation of image segmentations by energy minimization. For building extraction, we apply fuzzy sets to create a fuzzy landscape of shadows which in turn involves a two-step procedure. The first step is a preliminarily image classification at a fine segmentation level to generate vegetation and shadow information. The second step models the directional relationship between building and shadow objects to extract building information at the optimal segmentation level. We conducted the experiments on two datasets of Pléiades images from Wuhan City, China. To demonstrate its performance, the proposed classification is compared at the optimal segmentation level with Maximum Likelihood Classification and Support Vector Machine classification. The results show that the proposed classification produced the highest overall accuracies and kappa coefficients, and the smallest over-classification and under-classification geometric errors. We conclude first that integrating BPT with energy minimization offers an effective means for image segmentation. Second, we conclude that the directional relationship between building and shadow objects represented by a fuzzy landscape is important for building extraction.

  15. Hyperspectral Image Classification Using Discriminative Dictionary Learning

    International Nuclear Information System (INIS)

    Zongze, Y; Hao, S; Kefeng, J; Huanxin, Z

    2014-01-01

    The hyperspectral image (HSI) processing community has witnessed a surge of papers focusing on the utilization of sparse prior for effective HSI classification. In sparse representation based HSI classification, there are two phases: sparse coding with an over-complete dictionary and classification. In this paper, we first apply a novel fisher discriminative dictionary learning method, which capture the relative difference in different classes. The competitive selection strategy ensures that atoms in the resulting over-complete dictionary are the most discriminative. Secondly, motivated by the assumption that spatially adjacent samples are statistically related and even belong to the same materials (same class), we propose a majority voting scheme incorporating contextual information to predict the category label. Experiment results show that the proposed method can effectively strengthen relative discrimination of the constructed dictionary, and incorporating with the majority voting scheme achieve generally an improved prediction performance

  16. Perspectives on Machine Learning for Classification of Schizotypy Using fMRI Data

    DEFF Research Database (Denmark)

    Madsen, Kristoffer Hougaard; Krohne, Laerke G; Cai, Xin-Lu

    2018-01-01

    Functional magnetic resonance imaging is capable of estimating functional activation and connectivity in the human brain, and lately there has been increased interest in the use of these functional modalities combined with machine learning for identification of psychiatric traits. While...... the use of machine learning schizotypy research. To this end, we describe common data processing steps while commenting on best practices and procedures. First, we introduce the important role of schizotypy to motivate the importance of reliable classification, and summarize existing machine learning....... We provide more detailed descriptions and software as supplementary material. Finally, we present current challenges in machine learning for classification of schizotypy and comment on future trends and perspectives....

  17. Automatic Classification Using Supervised Learning in a Medical Document Filtering Application.

    Science.gov (United States)

    Mostafa, J.; Lam, W.

    2000-01-01

    Presents a multilevel model of the information filtering process that permits document classification. Evaluates a document classification approach based on a supervised learning algorithm, measures the accuracy of the algorithm in a neural network that was trained to classify medical documents on cell biology, and discusses filtering…

  18. Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

    Science.gov (United States)

    Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

    2018-04-01

    In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

  19. ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECTORIENTED CLASSIFICATION

    Directory of Open Access Journals (Sweden)

    L. Ding

    2018-04-01

    Full Text Available In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

  20. Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification

    Directory of Open Access Journals (Sweden)

    Lu Bing

    2017-01-01

    Full Text Available We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL. After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM. Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

  1. Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification.

    Science.gov (United States)

    Bing, Lu; Wang, Wei

    2017-01-01

    We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM). Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

  2. [Severity classification of chronic obstructive pulmonary disease based on deep learning].

    Science.gov (United States)

    Ying, Jun; Yang, Ceyuan; Li, Quanzheng; Xue, Wanguo; Li, Tanshi; Cao, Wenzhe

    2017-12-01

    In this paper, a deep learning method has been raised to build an automatic classification algorithm of severity of chronic obstructive pulmonary disease. Large sample clinical data as input feature were analyzed for their weights in classification. Through feature selection, model training, parameter optimization and model testing, a classification prediction model based on deep belief network was built to predict severity classification criteria raised by the Global Initiative for Chronic Obstructive Lung Disease (GOLD). We get accuracy over 90% in prediction for two different standardized versions of severity criteria raised in 2007 and 2011 respectively. Moreover, we also got the contribution ranking of different input features through analyzing the model coefficient matrix and confirmed that there was a certain degree of agreement between the more contributive input features and the clinical diagnostic knowledge. The validity of the deep belief network model was proved by this result. This study provides an effective solution for the application of deep learning method in automatic diagnostic decision making.

  3. Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI

    Directory of Open Access Journals (Sweden)

    Ling-Li Zeng

    2018-04-01

    Full Text Available Background: A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. Methods: A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Findings: Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. Interpretation: The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the “disconnectivity” model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Keywords: Schizophrenia, Deep learning, Connectome, f

  4. Tweet-based Target Market Classification Using Ensemble Method

    Directory of Open Access Journals (Sweden)

    Muhammad Adi Khairul Anshary

    2016-09-01

    Full Text Available Target market classification is aimed at focusing marketing activities on the right targets. Classification of target markets can be done through data mining and by utilizing data from social media, e.g. Twitter. The end result of data mining are learning models that can classify new data. Ensemble methods can improve the accuracy of the models and therefore provide better results. In this study, classification of target markets was conducted on a dataset of 3000 tweets in order to extract features. Classification models were constructed to manipulate the training data using two ensemble methods (bagging and boosting. To investigate the effectiveness of the ensemble methods, this study used the CART (classification and regression tree algorithm for comparison. Three categories of consumer goods (computers, mobile phones and cameras and three categories of sentiments (positive, negative and neutral were classified towards three target-market categories. Machine learning was performed using Weka 3.6.9. The results of the test data showed that the bagging method improved the accuracy of CART with 1.9% (to 85.20%. On the other hand, for sentiment classification, the ensemble methods were not successful in increasing the accuracy of CART. The results of this study may be taken into consideration by companies who approach their customers through social media, especially Twitter.

  5. Stacked Denoising Autoencoders Applied to Star/Galaxy Classification

    Science.gov (United States)

    Qin, Hao-ran; Lin, Ji-ming; Wang, Jun-yi

    2017-04-01

    In recent years, the deep learning algorithm, with the characteristics of strong adaptability, high accuracy, and structural complexity, has become more and more popular, but it has not yet been used in astronomy. In order to solve the problem that the star/galaxy classification accuracy is high for the bright source set, but low for the faint source set of the Sloan Digital Sky Survey (SDSS) data, we introduced the new deep learning algorithm, namely the SDA (stacked denoising autoencoder) neural network and the dropout fine-tuning technique, which can greatly improve the robustness and antinoise performance. We randomly selected respectively the bright source sets and faint source sets from the SDSS DR12 and DR7 data with spectroscopic measurements, and made preprocessing on them. Then, we randomly selected respectively the training sets and testing sets without replacement from the bright source sets and faint source sets. At last, using these training sets we made the training to obtain the SDA models of the bright sources and faint sources in the SDSS DR7 and DR12, respectively. We compared the test result of the SDA model on the DR12 testing set with the test results of the Library for Support Vector Machines (LibSVM), J48 decision tree, Logistic Model Tree (LMT), Support Vector Machine (SVM), Logistic Regression, and Decision Stump algorithm, and compared the test result of the SDA model on the DR7 testing set with the test results of six kinds of decision trees. The experiments show that the SDA has a better classification accuracy than other machine learning algorithms for the faint source sets of DR7 and DR12. Especially, when the completeness function is used as the evaluation index, compared with the decision tree algorithms, the correctness rate of SDA has improved about 15% for the faint source set of SDSS-DR7.

  6. Active learning for clinical text classification: is it better than random sampling?

    Science.gov (United States)

    Figueroa, Rosa L; Ngo, Long H; Goryachev, Sergey; Wiechmann, Eduardo P

    2012-01-01

    Objective This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks. Design Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results. Measurements Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences. Results The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm. Conclusion For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty. PMID:22707743

  7. An edit script for taxonomic classifications

    Directory of Open Access Journals (Sweden)

    Valiente Gabriel

    2005-08-01

    Full Text Available Abstract Background The NCBI taxonomy provides one of the most powerful ways to navigate sequence data bases but currently users are forced to formulate queries according to a single taxonomic classification. Given that there is not universal agreement on the classification of organisms, providing a single classification places constraints on the questions biologists can ask. However, maintaining multiple classifications is burdensome in the face of a constantly growing NCBI classification. Results In this paper, we present a solution to the problem of generating modifications of the NCBI taxonomy, based on the computation of an edit script that summarises the differences between two classification trees. Our algorithms find the shortest possible edit script based on the identification of all shared subtrees, and only take time quasi linear in the size of the trees because classification trees have unique node labels. Conclusion These algorithms have been recently implemented, and the software is freely available for download from http://darwin.zoology.gla.ac.uk/~rpage/forest/.

  8. BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

    Directory of Open Access Journals (Sweden)

    F. Pirotti

    2016-06-01

    Full Text Available Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels for testing and validating subsets. The classes used are the following: (i urban (ii sowable areas (iii water (iv tree plantations (v grasslands. Validation is carried out using three different approaches: (i using pixels from the training dataset (train, (ii using pixels from the training dataset and applying cross-validation with the k-fold method (kfold and (iii using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train, the whole control dataset (full and with k-fold cross-validation (kfold with ten folds. Results from validation of predictions of the whole dataset (full show the

  9. Supervised Learning Applied to Air Traffic Trajectory Classification

    Science.gov (United States)

    Bosson, Christabelle; Nikoleris, Tasos

    2018-01-01

    Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

  10. A cross-cultural investigation of college student alcohol consumption: a classification tree analysis.

    Science.gov (United States)

    Kitsantas, Panagiota; Kitsantas, Anastasia; Anagnostopoulou, Tanya

    2008-01-01

    In this cross-cultural study, the authors attempted to identify high-risk subgroups for alcohol consumption among college students. American and Greek students (N = 132) answered questions about alcohol consumption, religious beliefs, attitudes toward drinking, advertisement influences, parental monitoring, and drinking consequences. Heavy drinkers in the American group were younger and less religious than were infrequent drinkers. In the Greek group, heavy drinkers tended to deny the negative results of drinking alcohol and use a permissive attitude to justify it, whereas infrequent drinkers were more likely to be monitored by their parents. These results suggest that parental monitoring and an emphasis on informing students about the negative effects of alcohol on their health and social and academic lives may be effective methods of reducing alcohol consumption. Classification tree analysis revealed that student attitudes toward drinking were important in the classification of American and Greek drinkers, indicating that this is a powerful predictor of alcohol consumption regardless of ethnic background.

  11. Signal classification for acoustic neutrino detection

    International Nuclear Information System (INIS)

    Neff, M.; Anton, G.; Enzenhöfer, A.; Graf, K.; Hößl, J.; Katz, U.; Lahmann, R.; Richardt, C.

    2012-01-01

    This article focuses on signal classification for deep-sea acoustic neutrino detection. In the deep sea, the background of transient signals is very diverse. Approaches like matched filtering are not sufficient to distinguish between neutrino-like signals and other transient signals with similar signature, which are forming the acoustic background for neutrino detection in the deep-sea environment. A classification system based on machine learning algorithms is analysed with the goal to find a robust and effective way to perform this task. For a well-trained model, a testing error on the level of 1% is achieved for strong classifiers like Random Forest and Boosting Trees using the extracted features of the signal as input and utilising dense clusters of sensors instead of single sensors.

  12. Advances in Patient Classification for Traditional Chinese Medicine: A Machine Learning Perspective

    Directory of Open Access Journals (Sweden)

    Changbo Zhao

    2015-01-01

    data analyzed by different computational methods, we present the overview for four subfields of TCM diagnosis, respectively. For each subfield, we design a rectangular reference list with applications in the horizontal direction and machine learning algorithms in the longitudinal direction. According to the current development of objective TCM diagnosis for patient classification, a discussion of the research issues around machine learning techniques with applications to TCM diagnosis is given to facilitate the further research for TCM patient classification.

  13. Classifying smoking urges via machine learning.

    Science.gov (United States)

    Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

    2016-12-01

    Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. Copyright © 2016 Elsevier Ireland Ltd. All rights

  14. Tree Colors: Color Schemes for Tree-Structured Data.

    Science.gov (United States)

    Tennekes, Martijn; de Jonge, Edwin

    2014-12-01

    We present a method to map tree structures to colors from the Hue-Chroma-Luminance color model, which is known for its well balanced perceptual properties. The Tree Colors method can be tuned with several parameters, whose effect on the resulting color schemes is discussed in detail. We provide a free and open source implementation with sensible parameter defaults. Categorical data are very common in statistical graphics, and often these categories form a classification tree. We evaluate applying Tree Colors to tree structured data with a survey on a large group of users from a national statistical institute. Our user study suggests that Tree Colors are useful, not only for improving node-link diagrams, but also for unveiling tree structure in non-hierarchical visualizations.

  15. Transportation Modes Classification Using Sensors on Smartphones

    Directory of Open Access Journals (Sweden)

    Shih-Hau Fang

    2016-08-01

    Full Text Available This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.

  16. Practical secure decision tree learning in a teletreatment application

    NARCIS (Netherlands)

    de Hoogh, Sebastiaan; Schoenmakers, Berry; Chen, Ping; op den Akker, Harm

    In this paper we develop a range of practical cryptographic protocols for secure decision tree learning, a primary problem in privacy preserving data mining. We focus on particular variants of the well-known ID3 algorithm allowing a high level of security and performance at the same time. Our

  17. Practical secure decision tree learning in a teletreatment application

    NARCIS (Netherlands)

    Hoogh, de S.J.A.; Schoenmakers, B.; Chen, Ping; Op den Akker, H.; Christin, N.; Safavi-Naini, R.

    2014-01-01

    In this paper we develop a range of practical cryptographic protocols for secure decision tree learning, a primary problem in privacy preserving data mining. We focus on particular variants of the well-known ID3 algorithm allowing a high level of security and performance at the same time. Our

  18. A novel deep learning approach for classification of EEG motor imagery signals.

    Science.gov (United States)

    Tabar, Yousef Rezaei; Halici, Ugur

    2017-02-01

    Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

  19. Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI.

    Science.gov (United States)

    Zeng, Ling-Li; Wang, Huaning; Hu, Panpan; Yang, Bo; Pu, Weidan; Shen, Hui; Chen, Xingui; Liu, Zhening; Yin, Hong; Tan, Qingrong; Wang, Kai; Hu, Dewen

    2018-04-01

    A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Copyright © 2018 German Center for Neurodegenerative Diseases (DZNE). Published by Elsevier B.V. All rights reserved.

  20. Prediction of lung cancer patient survival via supervised machine learning classification techniques.

    Science.gov (United States)

    Lynch, Chip M; Abdollahi, Behnaz; Fuqua, Joshua D; de Carlo, Alexandra R; Bartholomai, James A; Balgemann, Rayeanne N; van Berkel, Victor H; Frieboes, Hermann B

    2017-12-01

    Outcomes for cancer patients have been previously estimated by applying various machine learning techniques to large datasets such as the Surveillance, Epidemiology, and End Results (SEER) program database. In particular for lung cancer, it is not well understood which types of techniques would yield more predictive information, and which data attributes should be used in order to determine this information. In this study, a number of supervised learning techniques is applied to the SEER database to classify lung cancer patients in terms of survival, including linear regression, Decision Trees, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and a custom ensemble. Key data attributes in applying these methods include tumor grade, tumor size, gender, age, stage, and number of primaries, with the goal to enable comparison of predictive power between the various methods The prediction is treated like a continuous target, rather than a classification into categories, as a first step towards improving survival prediction. The results show that the predicted values agree with actual values for low to moderate survival times, which constitute the majority of the data. The best performing technique was the custom ensemble with a Root Mean Square Error (RMSE) value of 15.05. The most influential model within the custom ensemble was GBM, while Decision Trees may be inapplicable as it had too few discrete outputs. The results further show that among the five individual models generated, the most accurate was GBM with an RMSE value of 15.32. Although SVM underperformed with an RMSE value of 15.82, statistical analysis singles the SVM as the only model that generated a distinctive output. The results of the models are consistent with a classical Cox proportional hazards model used as a reference technique. We conclude that application of these supervised learning techniques to lung cancer data in the SEER database may be of use to estimate patient survival time

  1. Online Learning for Classification of Alzheimer Disease based on Cortical Thickness and Hippocampal Shape Analysis.

    Science.gov (United States)

    Lee, Ga-Young; Kim, Jeonghun; Kim, Ju Han; Kim, Kiwoong; Seong, Joon-Kyung

    2014-01-01

    Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33% (sensitivity 96.49% and specificity 64.33%). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52% (sensitivity 96.79% and specificity 63.24%). In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.

  2. Effect of e-learning program on risk assessment and pressure ulcer classification - A randomized study.

    Science.gov (United States)

    Bredesen, Ida Marie; Bjøro, Karen; Gunningberg, Lena; Hofoss, Dag

    2016-05-01

    Pressure ulcers (PUs) are a problem in health care. Staff competency is paramount to PU prevention. Education is essential to increase skills in pressure ulcer classification and risk assessment. Currently, no pressure ulcer learning programs are available in Norwegian. Develop and test an e-learning program for assessment of pressure ulcer risk and pressure ulcer classification. Forty-four nurses working in acute care hospital wards or nursing homes participated and were assigned randomly into two groups: an e-learning program group (intervention) and a traditional classroom lecture group (control). Data was collected immediately before and after training, and again after three months. The study was conducted at one nursing home and two hospitals between May and December 2012. Accuracy of risk assessment (five patient cases) and pressure ulcer classification (40 photos [normal skin, pressure ulcer categories I-IV] split in two sets) were measured by comparing nurse evaluations in each of the two groups to a pre-established standard based on ratings by experts in pressure ulcer classification and risk assessment. Inter-rater reliability was measured by exact percent agreement and multi-rater Fleiss kappa. A Mann-Whitney U test was used for continuous sum score variables. An e-learning program did not improve Braden subscale scoring. For pressure ulcer classification, however, the intervention group scored significantly higher than the control group on several of the categories in post-test immediately after training. However, after three months there were no significant differences in classification skills between the groups. An e-learning program appears to have a greater effect on the accuracy of pressure ulcer classification than classroom teaching in the short term. For proficiency in Braden scoring, no significant effect of educational methods on learning results was detected. Copyright © 2016 Elsevier Ltd. All rights reserved.

  3. Deep learning decision fusion for the classification of urban remote sensing data

    Science.gov (United States)

    Abdi, Ghasem; Samadzadegan, Farhad; Reinartz, Peter

    2018-01-01

    Multisensor data fusion is one of the most common and popular remote sensing data classification topics by considering a robust and complete description about the objects of interest. Furthermore, deep feature extraction has recently attracted significant interest and has become a hot research topic in the geoscience and remote sensing research community. A deep learning decision fusion approach is presented to perform multisensor urban remote sensing data classification. After deep features are extracted by utilizing joint spectral-spatial information, a soft-decision made classifier is applied to train high-level feature representations and to fine-tune the deep learning framework. Next, a decision-level fusion classifies objects of interest by the joint use of sensors. Finally, a context-aware object-based postprocessing is used to enhance the classification results. A series of comparative experiments are conducted on the widely used dataset of 2014 IEEE GRSS data fusion contest. The obtained results illustrate the considerable advantages of the proposed deep learning decision fusion over the traditional classifiers.

  4. Classification of EEG signals using a genetic-based machine learning classifier.

    Science.gov (United States)

    Skinner, B T; Nguyen, H T; Liu, D K

    2007-01-01

    This paper investigates the efficacy of the genetic-based learning classifier system XCS, for the classification of noisy, artefact-inclusive human electroencephalogram (EEG) signals represented using large condition strings (108bits). EEG signals from three participants were recorded while they performed four mental tasks designed to elicit hemispheric responses. Autoregressive (AR) models and Fast Fourier Transform (FFT) methods were used to form feature vectors with which mental tasks can be discriminated. XCS achieved a maximum classification accuracy of 99.3% and a best average of 88.9%. The relative classification performance of XCS was then compared against four non-evolutionary classifier systems originating from different learning techniques. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices.

  5. Generative Adversarial Networks-Based Semi-Supervised Learning for Hyperspectral Image Classification

    Directory of Open Access Journals (Sweden)

    Zhi He

    2017-10-01

    Full Text Available Classification of hyperspectral image (HSI is an important research topic in the remote sensing community. Significant efforts (e.g., deep learning have been concentrated on this task. However, it is still an open issue to classify the high-dimensional HSI with a limited number of training samples. In this paper, we propose a semi-supervised HSI classification method inspired by the generative adversarial networks (GANs. Unlike the supervised methods, the proposed HSI classification method is semi-supervised, which can make full use of the limited labeled samples as well as the sufficient unlabeled samples. Core ideas of the proposed method are twofold. First, the three-dimensional bilateral filter (3DBF is adopted to extract the spectral-spatial features by naturally treating the HSI as a volumetric dataset. The spatial information is integrated into the extracted features by 3DBF, which is propitious to the subsequent classification step. Second, GANs are trained on the spectral-spatial features for semi-supervised learning. A GAN contains two neural networks (i.e., generator and discriminator trained in opposition to one another. The semi-supervised learning is achieved by adding samples from the generator to the features and increasing the dimension of the classifier output. Experimental results obtained on three benchmark HSI datasets have confirmed the effectiveness of the proposed method , especially with a limited number of labeled samples.

  6. Temporal expansion of annual crop classification layers for the CONUS using the C5 decision tree classifier

    Science.gov (United States)

    Friesz, Aaron M.; Wylie, Bruce K.; Howard, Daniel M.

    2017-01-01

    Crop cover maps have become widely used in a range of research applications. Multiple crop cover maps have been developed to suite particular research interests. The National Agricultural Statistics Service (NASS) Cropland Data Layers (CDL) are a series of commonly used crop cover maps for the conterminous United States (CONUS) that span from 2008 to 2013. In this investigation, we sought to contribute to the availability of consistent CONUS crop cover maps by extending temporal coverage of the NASS CDL archive back eight additional years to 2000 by creating annual NASS CDL-like crop cover maps derived from a classification tree model algorithm. We used over 11 million records to train a classification tree algorithm and develop a crop classification model (CCM). The model was used to create crop cover maps for the CONUS for years 2000–2013 at 250 m spatial resolution. The CCM and the maps for years 2008–2013 were assessed for accuracy relative to resampled NASS CDLs. The CCM performed well against a withheld test data set with a model prediction accuracy of over 90%. The assessment of the crop cover maps indicated that the model performed well spatially, placing crop cover pixels within their known domains; however, the model did show a bias towards the ‘Other’ crop cover class, which caused frequent misclassifications of pixels around the periphery of large crop cover patch clusters and of pixels that form small, sparsely dispersed crop cover patches.

  7. Ichthyoplankton Classification Tool using Generative Adversarial Networks and Transfer Learning

    KAUST Repository

    Aljaafari, Nura

    2018-04-15

    The study and the analysis of marine ecosystems is a significant part of the marine science research. These systems are valuable resources for fisheries, improving water quality and can even be used in drugs production. The investigation of ichthyoplankton inhabiting these ecosystems is also an important research field. Ichthyoplankton are fish in their early stages of life. In this stage, the fish have relatively similar shape and are small in size. The currently used way of identifying them is not optimal. Marine scientists typically study such organisms by sending a team that collects samples from the sea which is then taken to the lab for further investigation. These samples need to be studied by an expert and usually end needing a DNA sequencing. This method is time-consuming and requires a high level of experience. The recent advances in AI have helped to solve and automate several difficult tasks which motivated us to develop a classification tool for ichthyoplankton. We show that using machine learning techniques, such as generative adversarial networks combined with transfer learning solves such a problem with high accuracy. We show that using traditional machine learning algorithms fails to solve it. We also give a general framework for creating a classification tool when the dataset used for training is a limited dataset. We aim to build a user-friendly tool that can be used by any user for the classification task and we aim to give a guide to the researchers so that they can follow in creating a classification tool.

  8. QUEST : Eliminating online supervised learning for efficient classification algorithms

    NARCIS (Netherlands)

    Zwartjes, Ardjan; Havinga, Paul J.M.; Smit, Gerard J.M.; Hurink, Johann L.

    2016-01-01

    In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting

  9. [Guidelines for hygienic classification of learning technologies].

    Science.gov (United States)

    Kuchma, V R; Teksheva, L M; Milushkina, O Iu

    2008-01-01

    Optimization of the educational environment under the present-day conditions has been in progress, by using learning techwares (LTW) without fail. To organize and regulate an academic process in terms of the safety of applied LTW, there is a need for their classification. The currently existing attempts to structure LTW disregard hygienically significant aspects. The task of the present study was to substantiate a LTW safety criterion ensuring a universal approach to working out regulations. This criterion may be the exposure intensity determined by the form of organization of education and its pattern, by the procedure of information presentation, and the age-related peculiarities of a pupil, i.e. by the actual load that is presented by the product of the intensity exposure and its time. The hygienic classification of LTW may be used to evaluate their negative effect in an educational process on the health status of children and adolescents, to regulate hazardous factors and training modes, to design and introduce new learning complexes. The structuring of a LTW system allows one to define possible deleterious actions and the possibilities of preventing this action on the basis of strictly established regulations.

  10. Medical Dataset Classification: A Machine Learning Paradigm Integrating Particle Swarm Optimization with Extreme Learning Machine Classifier

    Directory of Open Access Journals (Sweden)

    C. V. Subbulakshmi

    2015-01-01

    Full Text Available Medical data classification is a prime data mining problem being discussed about for a decade that has attracted several researchers around the world. Most classifiers are designed so as to learn from the data itself using a training process, because complete expert knowledge to determine classifier parameters is impracticable. This paper proposes a hybrid methodology based on machine learning paradigm. This paradigm integrates the successful exploration mechanism called self-regulated learning capability of the particle swarm optimization (PSO algorithm with the extreme learning machine (ELM classifier. As a recent off-line learning method, ELM is a single-hidden layer feedforward neural network (FFNN, proved to be an excellent classifier with large number of hidden layer neurons. In this research, PSO is used to determine the optimum set of parameters for the ELM, thus reducing the number of hidden layer neurons, and it further improves the network generalization performance. The proposed method is experimented on five benchmarked datasets of the UCI Machine Learning Repository for handling medical dataset classification. Simulation results show that the proposed approach is able to achieve good generalization performance, compared to the results of other classifiers.

  11. APPLICATION OF MULTIPLE LOGISTIC REGRESSION, BAYESIAN LOGISTIC AND CLASSIFICATION TREE TO IDENTIFY THE SIGNIFICANT FACTORS INFLUENCING CRASH SEVERITY

    Directory of Open Access Journals (Sweden)

    MILAD TAZIK

    2017-11-01

    Full Text Available Identifying cases in which road crashes result in fatality or injury of drivers may help improve their safety. In this study, datasets of crashes happened in TehranQom freeway, Iran, were examined by three models (multiple logistic regression, Bayesian logistic and classification tree to analyse the contribution of several variables to fatal accidents. For multiple logistic regression and Bayesian logistic models, the odds ratio was calculated for each variable. The model which best suited the identification of accident severity was determined based on AIC and DIC criteria. Based on the results of these two models, rollover crashes (OR = 14.58, %95 CI: 6.8-28.6, not using of seat belt (OR = 5.79, %95 CI: 3.1-9.9, exceeding speed limits (OR = 4.02, %95 CI: 1.8-7.9 and being female (OR = 2.91, %95 CI: 1.1-6.1 were the most important factors in fatalities of drivers. In addition, the results of the classification tree model have verified the findings of the other models.

  12. Tree Nut Allergies

    Science.gov (United States)

    ... Blog Vision Awards Common Allergens Tree Nut Allergy Tree Nut Allergy Learn about tree nut allergy, how ... a Tree Nut Label card . Allergic Reactions to Tree Nuts Tree nuts can cause a severe and ...

  13. Adapting and Evaluating a Tree of Life Group for Women with Learning Disabilities

    Science.gov (United States)

    Randle-Phillips, Cathy; Farquhar, Sarah; Thomas, Sally

    2016-01-01

    Background: This study describes how a specific narrative therapy approach called 'the tree of life' was adapted to run a group for women with learning disabilities. The group consisted of four participants and ran for five consecutive weeks. Materials and Methods: Participants each constructed a tree to represent their lives and presented their…

  14. A fast learning method for large scale and multi-class samples of SVM

    Science.gov (United States)

    Fan, Yu; Guo, Huiming

    2017-06-01

    A multi-class classification SVM(Support Vector Machine) fast learning method based on binary tree is presented to solve its low learning efficiency when SVM processing large scale multi-class samples. This paper adopts bottom-up method to set up binary tree hierarchy structure, according to achieved hierarchy structure, sub-classifier learns from corresponding samples of each node. During the learning, several class clusters are generated after the first clustering of the training samples. Firstly, central points are extracted from those class clusters which just have one type of samples. For those which have two types of samples, cluster numbers of their positive and negative samples are set respectively according to their mixture degree, secondary clustering undertaken afterwards, after which, central points are extracted from achieved sub-class clusters. By learning from the reduced samples formed by the integration of extracted central points above, sub-classifiers are obtained. Simulation experiment shows that, this fast learning method, which is based on multi-level clustering, can guarantee higher classification accuracy, greatly reduce sample numbers and effectively improve learning efficiency.

  15. Overfitting Reduction of Text Classification Based on AdaBELM

    Directory of Open Access Journals (Sweden)

    Xiaoyue Feng

    2017-07-01

    Full Text Available Overfitting is an important problem in machine learning. Several algorithms, such as the extreme learning machine (ELM, suffer from this issue when facing high-dimensional sparse data, e.g., in text classification. One common issue is that the extent of overfitting is not well quantified. In this paper, we propose a quantitative measure of overfitting referred to as the rate of overfitting (RO and a novel model, named AdaBELM, to reduce the overfitting. With RO, the overfitting problem can be quantitatively measured and identified. The newly proposed model can achieve high performance on multi-class text classification. To evaluate the generalizability of the new model, we designed experiments based on three datasets, i.e., the 20 Newsgroups, Reuters-21578, and BioMed corpora, which represent balanced, unbalanced, and real application data, respectively. Experiment results demonstrate that AdaBELM can reduce overfitting and outperform classical ELM, decision tree, random forests, and AdaBoost on all three text-classification datasets; for example, it can achieve 62.2% higher accuracy than ELM. Therefore, the proposed model has a good generalizability.

  16. Using Machine Learning to Predict Student Performance

    OpenAIRE

    Pojon, Murat

    2017-01-01

    This thesis examines the application of machine learning algorithms to predict whether a student will be successful or not. The specific focus of the thesis is the comparison of machine learning methods and feature engineering techniques in terms of how much they improve the prediction performance. Three different machine learning methods were used in this thesis. They are linear regression, decision trees, and naïve Bayes classification. Feature engineering, the process of modification ...

  17. Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images

    Directory of Open Access Journals (Sweden)

    Marc Wieland

    2014-03-01

    Full Text Available In this study, a classification and performance evaluation framework for the recognition of urban patterns in medium (Landsat ETM, TM and MSS and very high resolution (WorldView-2, Quickbird, Ikonos multi-spectral satellite images is presented. The study aims at exploring the potential of machine learning algorithms in the context of an object-based image analysis and to thoroughly test the algorithm’s performance under varying conditions to optimize their usage for urban pattern recognition tasks. Four classification algorithms, Normal Bayes, K Nearest Neighbors, Random Trees and Support Vector Machines, which represent different concepts in machine learning (probabilistic, nearest neighbor, tree-based, function-based, have been selected and implemented on a free and open-source basis. Particular focus is given to assess the generalization ability of machine learning algorithms and the transferability of trained learning machines between different image types and image scenes. Moreover, the influence of the number and choice of training data, the influence of the size and composition of the feature vector and the effect of image segmentation on the classification accuracy is evaluated.

  18. Solar wind classification from a machine learning perspective

    Science.gov (United States)

    Heidrich-Meisner, V.; Wimmer-Schweingruber, R. F.

    2017-12-01

    It is a very well known fact that the ubiquitous solar wind comes in at least two varieties, the slow solar wind and the coronal hole wind. The simplified view of two solar wind types has been frequently challenged. Existing solar wind categorization schemes rely mainly on different combinations of the solar wind proton speed, the O and C charge state ratios, the Alfvén speed, the expected proton temperature and the specific proton entropy. In available solar wind classification schemes, solar wind from stream interaction regimes is often considered either as coronal hole wind or slow solar wind, although their plasma properties are different compared to "pure" coronal hole or slow solar wind. As shown in Neugebauer et al. (2016), even if only two solar wind types are assumed, available solar wind categorization schemes differ considerably for intermediate solar wind speeds. Thus, the decision boundary between the coronal hole and the slow solar wind is so far not well defined.In this situation, a machine learning approach to solar wind classification can provide an additional perspective.We apply a well-known machine learning method, k-means, to the task of solar wind classification in order to answer the following questions: (1) How many solar wind types can reliably be identified in our data set comprised of ten years of solar wind observations from the Advanced Composition Explorer (ACE)? (2) Which combinations of solar wind parameters are particularly useful for solar wind classification?Potential subtypes of slow solar wind are of particular interest because they can provide hints of respective different source regions or release mechanisms of slow solar wind.

  19. A dictionary learning approach for human sperm heads classification.

    Science.gov (United States)

    Shaker, Fariba; Monadjemi, S Amirhassan; Alirezaie, Javad; Naghsh-Nilchi, Ahmad Reza

    2017-12-01

    To diagnose infertility in men, semen analysis is conducted in which sperm morphology is one of the factors that are evaluated. Since manual assessment of sperm morphology is time-consuming and subjective, automatic classification methods are being developed. Automatic classification of sperm heads is a complicated task due to the intra-class differences and inter-class similarities of class objects. In this research, a Dictionary Learning (DL) technique is utilized to construct a dictionary of sperm head shapes. This dictionary is used to classify the sperm heads into four different classes. Square patches are extracted from the sperm head images. Columnized patches from each class of sperm are used to learn class-specific dictionaries. The patches from a test image are reconstructed using each class-specific dictionary and the overall reconstruction error for each class is used to select the best matching class. Average accuracy, precision, recall, and F-score are used to evaluate the classification method. The method is evaluated using two publicly available datasets of human sperm head shapes. The proposed DL based method achieved an average accuracy of 92.2% on the HuSHeM dataset, and an average recall of 62% on the SCIAN-MorphoSpermGS dataset. The results show a significant improvement compared to a previously published shape-feature-based method. We have achieved high-performance results. In addition, our proposed approach offers a more balanced classifier in which all four classes are recognized with high precision and recall. In this paper, we use a Dictionary Learning approach in classifying human sperm heads. It is shown that the Dictionary Learning method is far more effective in classifying human sperm heads than classifiers using shape-based features. Also, a dataset of human sperm head shapes is introduced to facilitate future research. Copyright © 2017 Elsevier Ltd. All rights reserved.

  20. Two Trees: Migrating Fault Trees to Decision Trees for Real Time Fault Detection on International Space Station

    Science.gov (United States)

    Lee, Charles; Alena, Richard L.; Robinson, Peter

    2004-01-01

    We started from ISS fault trees example to migrate to decision trees, presented a method to convert fault trees to decision trees. The method shows that the visualizations of root cause of fault are easier and the tree manipulating becomes more programmatic via available decision tree programs. The visualization of decision trees for the diagnostic shows a format of straight forward and easy understands. For ISS real time fault diagnostic, the status of the systems could be shown by mining the signals through the trees and see where it stops at. The other advantage to use decision trees is that the trees can learn the fault patterns and predict the future fault from the historic data. The learning is not only on the static data sets but also can be online, through accumulating the real time data sets, the decision trees can gain and store faults patterns in the trees and recognize them when they come.

  1. Nonparametric, Coupled ,Bayesian ,Dictionary ,and Classifier Learning for Hyperspectral Classification.

    Science.gov (United States)

    Akhtar, Naveed; Mian, Ajmal

    2017-10-03

    We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.

  2. Spatial-temporal changes in trees outside forests

    DEFF Research Database (Denmark)

    Novotný, M.; Skaloš, J.; Plieninger, T.

    2017-01-01

    Trees outside forests act as ecologically valuable elements in the rural landscapes of Europe. This study proposes a new classification system for trees outside forest elements based on the shape and size of the patches and their location in fields. Using this system, the study evaluates the spat......Trees outside forests act as ecologically valuable elements in the rural landscapes of Europe. This study proposes a new classification system for trees outside forest elements based on the shape and size of the patches and their location in fields. Using this system, the study evaluates...

  3. Classification of ECG beats using deep belief network and active learning.

    Science.gov (United States)

    G, Sayantan; T, Kien P; V, Kadambari K

    2018-04-12

    A new semi-supervised approach based on deep learning and active learning for classification of electrocardiogram signals (ECG) is proposed. The objective of the proposed work is to model a scientific method for classification of cardiac irregularities using electrocardiogram beats. The model follows the Association for the Advancement of medical instrumentation (AAMI) standards and consists of three phases. In phase I, feature representation of ECG is learnt using Gaussian-Bernoulli deep belief network followed by a linear support vector machine (SVM) training in the consecutive phase. It yields three deep models which are based on AAMI-defined classes, namely N, V, S, and F. In the last phase, a query generator is introduced to interact with the expert to label few beats to improve accuracy and sensitivity. The proposed approach depicts significant improvement in accuracy with minimal queries posed to the expert and fast online training as tested on the MIT-BIH Arrhythmia Database and the MIT-BIH Supra-ventricular Arrhythmia Database (SVDB). With 100 queries labeled by the expert in phase III, the method achieves an accuracy of 99.5% in "S" versus all classifications (SVEB) and 99.4% accuracy in "V " versus all classifications (VEB) on MIT-BIH Arrhythmia Database. In a similar manner, it is attributed that an accuracy of 97.5% for SVEB and 98.6% for VEB on SVDB database is achieved respectively. Graphical Abstract Reply- Deep belief network augmented by active learning for efficient prediction of arrhythmia.

  4. Automatic classification of 6-month-old infants at familial risk for language-based learning disorder using a support vector machine.

    Science.gov (United States)

    Zare, Marzieh; Rezvani, Zahra; Benasich, April A

    2016-07-01

    This study assesses the ability of a novel, "automatic classification" approach to facilitate identification of infants at highest familial risk for language-learning disorders (LLD) and to provide converging assessments to enable earlier detection of developmental disorders that disrupt language acquisition. Network connectivity measures derived from 62-channel electroencephalogram (EEG) recording were used to identify selected features within two infant groups who differed on LLD risk: infants with a family history of LLD (FH+) and typically-developing infants without such a history (FH-). A support vector machine was deployed; global efficiency and global and local clustering coefficients were computed. A novel minimum spanning tree (MST) approach was also applied. Cross-validation was employed to assess the resultant classification. Infants were classified with about 80% accuracy into FH+ and FH- groups with 89% specificity and precision of 92%. Clustering patterns differed by risk group and MST network analysis suggests that FH+ infants' EEG complexity patterns were significantly different from FH- infants. The automatic classification techniques used here were shown to be both robust and reliable and should provide valuable information when applied to early identification of risk or clinical groups. The ability to identify infants at highest risk for LLD using "automatic classification" strategies is a novel convergent approach that may facilitate earlier diagnosis and remediation. Copyright © 2016 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

  5. Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees

    International Nuclear Information System (INIS)

    Jerebko, Anna K.; Summers, Ronald M.; Malley, James D.; Franaszek, Marek; Johnson, C. Daniel

    2003-01-01

    Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study

  6. Weakly Supervised Dictionary Learning

    Science.gov (United States)

    You, Zeyu; Raich, Raviv; Fern, Xiaoli Z.; Kim, Jinsub

    2018-05-01

    We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising and restoration as well as high-level classification tasks, which can be applied to audio and image analysis. Synthesis dictionary learning aims at jointly learning a dictionary and corresponding sparse coefficients to provide accurate data representation. This approach is useful for denoising and signal restoration, but may lead to sub-optimal classification performance. By contrast, analysis dictionary learning provides a transform that maps data to a sparse discriminative representation suitable for classification. We consider the problem of analysis dictionary learning for time-series data under a weak supervision setting in which signals are assigned with a global label instead of an instantaneous label signal. We propose a discriminative probabilistic model that incorporates both label information and sparsity constraints on the underlying latent instantaneous label signal using cardinality control. We present the expectation maximization (EM) procedure for maximum likelihood estimation (MLE) of the proposed model. To facilitate a computationally efficient E-step, we propose both a chain and a novel tree graph reformulation of the graphical model. The performance of the proposed model is demonstrated on both synthetic and real-world data.

  7. Coupled dimensionality reduction and classification for supervised and semi-supervised multilabel learning.

    Science.gov (United States)

    Gönen, Mehmet

    2014-03-01

    Coupled training of dimensionality reduction and classification is proposed previously to improve the prediction performance for single-label problems. Following this line of research, in this paper, we first introduce a novel Bayesian method that combines linear dimensionality reduction with linear binary classification for supervised multilabel learning and present a deterministic variational approximation algorithm to learn the proposed probabilistic model. We then extend the proposed method to find intrinsic dimensionality of the projected subspace using automatic relevance determination and to handle semi-supervised learning using a low-density assumption. We perform supervised learning experiments on four benchmark multilabel learning data sets by comparing our method with baseline linear dimensionality reduction algorithms. These experiments show that the proposed approach achieves good performance values in terms of hamming loss, average AUC, macro F 1 , and micro F 1 on held-out test data. The low-dimensional embeddings obtained by our method are also very useful for exploratory data analysis. We also show the effectiveness of our approach in finding intrinsic subspace dimensionality and semi-supervised learning tasks.

  8. First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe

    OpenAIRE

    Markus Immitzer; Francesco Vuolo; Clement Atzberger

    2016-01-01

    The study presents the preliminary results of two classification exercises assessing the capabilities of pre-operational (August 2015) Sentinel-2 (S2) data for mapping crop types and tree species. In the first case study, an S2 image was used to map six summer crop species in Lower Austria as well as winter crops/bare soil. Crop type maps are needed to account for crop-specific water use and for agricultural statistics. Crop type information is also useful to parametrize crop growth models fo...

  9. Integrating classification trees with local logistic regression in Intensive Care prognosis.

    Science.gov (United States)

    Abu-Hanna, Ameen; de Keizer, Nicolette

    2003-01-01

    Health care effectiveness and efficiency are under constant scrutiny especially when treatment is quite costly as in the Intensive Care (IC). Currently there are various international quality of care programs for the evaluation of IC. At the heart of such quality of care programs lie prognostic models whose prediction of patient mortality can be used as a norm to which actual mortality is compared. The current generation of prognostic models in IC are statistical parametric models based on logistic regression. Given a description of a patient at admission, these models predict the probability of his or her survival. Typically, this patient description relies on an aggregate variable, called a score, that quantifies the severity of illness of the patient. The use of a parametric model and an aggregate score form adequate means to develop models when data is relatively scarce but it introduces the risk of bias. This paper motivates and suggests a method for studying and improving the performance behavior of current state-of-the-art IC prognostic models. Our method is based on machine learning and statistical ideas and relies on exploiting information that underlies a score variable. In particular, this underlying information is used to construct a classification tree whose nodes denote patient sub-populations. For these sub-populations, local models, most notably logistic regression ones, are developed using only the total score variable. We compare the performance of this hybrid model to that of a traditional global logistic regression model. We show that the hybrid model not only provides more insight into the data but also has a better performance. We pay special attention to the precision aspect of model performance and argue why precision is more important than discrimination ability.

  10. Using decision trees and their ensembles for analysis of NIR spectroscopic data

    DEFF Research Database (Denmark)

    Kucheryavskiy, Sergey V.

    and interpretation of the models. In this presentation, we are going to discuss an applicability of decision trees based methods (including gradient boosting) for solving classification and regression tasks with NIR spectra as predictors. We will cover such aspects as evaluation, optimization and validation......Advanced machine learning methods, like convolutional neural networks and decision trees, became extremely popular in the last decade. This, first of all, is directly related to the current boom in Big data analysis, where traditional statistical methods are not efficient. According to the kaggle.......com — the most popular online resource for Big data problems and solutions — methods based on decision trees and their ensembles are most widely used for solving the problems. It can be noted that the decision trees and convolutional neural networks are not very popular in Chemometrics. One of the reasons...

  11. More than one kind of inference: re-examining what's learned in feature inference and classification.

    Science.gov (United States)

    Sweller, Naomi; Hayes, Brett K

    2010-08-01

    Three studies examined how task demands that impact on attention to typical or atypical category features shape the category representations formed through classification learning and inference learning. During training categories were learned via exemplar classification or by inferring missing exemplar features. In the latter condition inferences were made about missing typical features alone (typical feature inference) or about both missing typical and atypical features (mixed feature inference). Classification and mixed feature inference led to the incorporation of typical and atypical features into category representations, with both kinds of features influencing inferences about familiar (Experiments 1 and 2) and novel (Experiment 3) test items. Those in the typical inference condition focused primarily on typical features. Together with formal modelling, these results challenge previous accounts that have characterized inference learning as producing a focus on typical category features. The results show that two different kinds of inference learning are possible and that these are subserved by different kinds of category representations.

  12. GENERATION OF 2D LAND COVER MAPS FOR URBAN AREAS USING DECISION TREE CLASSIFICATION

    DEFF Research Database (Denmark)

    Höhle, Joachim

    2014-01-01

    A 2D land cover map can automatically and efficiently be generated from high-resolution multispectral aerial images. First, a digital surface model is produced and each cell of the elevation model is then supplemented with attributes. A decision tree classification is applied to extract map objects...... of stereo-observations of false-colour stereopairs. The stratified statistical assessment of the produced land cover map with six classes and based on 91 points per class reveals a high thematic accuracy for classes ‘building’ (99%, 95% CI: 95%-100%) and ‘road and parking lot’ (90%, 95% CI: 83%-95%). Some...

  13. Fine-grained leukocyte classification with deep residual learning for microscopic images.

    Science.gov (United States)

    Qin, Feiwei; Gao, Nannan; Peng, Yong; Wu, Zizhao; Shen, Shuying; Grudtsin, Artur

    2018-08-01

    Leukocyte classification and cytometry have wide applications in medical domain, previous researches usually exploit machine learning techniques to classify leukocytes automatically. However, constrained by the past development of machine learning techniques, for example, extracting distinctive features from raw microscopic images are difficult, the widely used SVM classifier only has relative few parameters to tune, these methods cannot efficiently handle fine-grained classification cases when the white blood cells have up to 40 categories. Based on deep learning theory, a systematic study is conducted on finer leukocyte classification in this paper. A deep residual neural network based leukocyte classifier is constructed at first, which can imitate the domain expert's cell recognition process, and extract salient features robustly and automatically. Then the deep neural network classifier's topology is adjusted according to the prior knowledge of white blood cell test. After that the microscopic image dataset with almost one hundred thousand labeled leukocytes belonging to 40 categories is built, and combined training strategies are adopted to make the designed classifier has good generalization ability. The proposed deep residual neural network based classifier was tested on microscopic image dataset with 40 leukocyte categories. It achieves top-1 accuracy of 77.80%, top-5 accuracy of 98.75% during the training procedure. The average accuracy on the test set is nearly 76.84%. This paper presents a fine-grained leukocyte classification method for microscopic images, based on deep residual learning theory and medical domain knowledge. Experimental results validate the feasibility and effectiveness of our approach. Extended experiments support that the fine-grained leukocyte classifier could be used in real medical applications, assist doctors in diagnosing diseases, reduce human power significantly. Copyright © 2018 Elsevier B.V. All rights reserved.

  14. Identifying Different Transportation Modes from Trajectory Data Using Tree-Based Ensemble Classifiers

    Directory of Open Access Journals (Sweden)

    Zhibin Xiao

    2017-02-01

    Full Text Available Recognition of transportation modes can be used in different applications including human behavior research, transport management and traffic control. Previous work on transportation mode recognition has often relied on using multiple sensors or matching Geographic Information System (GIS information, which is not possible in many cases. In this paper, an approach based on ensemble learning is proposed to infer hybrid transportation modes using only Global Position System (GPS data. First, in order to distinguish between different transportation modes, we used a statistical method to generate global features and extract several local features from sub-trajectories after trajectory segmentation, before these features were combined in the classification stage. Second, to obtain a better performance, we used tree-based ensemble models (Random Forest, Gradient Boosting Decision Tree, and XGBoost instead of traditional methods (K-Nearest Neighbor, Decision Tree, and Support Vector Machines to classify the different transportation modes. The experiment results on the later have shown the efficacy of our proposed approach. Among them, the XGBoost model produced the best performance with a classification accuracy of 90.77% obtained on the GEOLIFE dataset, and we used a tree-based ensemble method to ensure accurate feature selection to reduce the model complexity.

  15. Deep learning architectures for multi-label classification of intelligent health risk prediction.

    Science.gov (United States)

    Maxwell, Andrew; Li, Runzhi; Yang, Bei; Weng, Heng; Ou, Aihua; Hong, Huixiao; Zhou, Zhaoxian; Gong, Ping; Zhang, Chaoyang

    2017-12-28

    Multi-label classification of data remains to be a challenging problem. Because of the complexity of the data, it is sometimes difficult to infer information about classes that are not mutually exclusive. For medical data, patients could have symptoms of multiple different diseases at the same time and it is important to develop tools that help to identify problems early. Intelligent health risk prediction models built with deep learning architectures offer a powerful tool for physicians to identify patterns in patient data that indicate risks associated with certain types of chronic diseases. Physical examination records of 110,300 anonymous patients were used to predict diabetes, hypertension, fatty liver, a combination of these three chronic diseases, and the absence of disease (8 classes in total). The dataset was split into training (90%) and testing (10%) sub-datasets. Ten-fold cross validation was used to evaluate prediction accuracy with metrics such as precision, recall, and F-score. Deep Learning (DL) architectures were compared with standard and state-of-the-art multi-label classification methods. Preliminary results suggest that Deep Neural Networks (DNN), a DL architecture, when applied to multi-label classification of chronic diseases, produced accuracy that was comparable to that of common methods such as Support Vector Machines. We have implemented DNNs to handle both problem transformation and algorithm adaption type multi-label methods and compare both to see which is preferable. Deep Learning architectures have the potential of inferring more information about the patterns of physical examination data than common classification methods. The advanced techniques of Deep Learning can be used to identify the significance of different features from physical examination data as well as to learn the contributions of each feature that impact a patient's risk for chronic diseases. However, accurate prediction of chronic disease risks remains a challenging

  16. Predicting the disease of Alzheimer with SNP biomarkers and clinical data using data mining classification approach: decision tree.

    Science.gov (United States)

    Erdoğan, Onur; Aydin Son, Yeşim

    2014-01-01

    Single Nucleotide Polymorphisms (SNPs) are the most common genomic variations where only a single nucleotide differs between individuals. Individual SNPs and SNP profiles associated with diseases can be utilized as biological markers. But there is a need to determine the SNP subsets and patients' clinical data which is informative for the diagnosis. Data mining approaches have the highest potential for extracting the knowledge from genomic datasets and selecting the representative SNPs as well as most effective and informative clinical features for the clinical diagnosis of the diseases. In this study, we have applied one of the widely used data mining classification methodology: "decision tree" for associating the SNP biomarkers and significant clinical data with the Alzheimer's disease (AD), which is the most common form of "dementia". Different tree construction parameters have been compared for the optimization, and the most accurate tree for predicting the AD is presented.

  17. Integrating Interview Methodology to Analyze Inter-Institutional Comparisons of Service-Learning within the Carnegie Community Engagement Classification Framework

    Science.gov (United States)

    Plante, Jarrad D.; Cox, Thomas D.

    2016-01-01

    Service-learning has a longstanding history in higher education in and includes three main tenets: academic learning, meaningful community service, and civic learning. The Carnegie Foundation for the Advancement of Teaching created an elective classification system called the Carnegie Community Engagement Classification for higher education…

  18. Assessment of various supervised learning algorithms using different performance metrics

    Science.gov (United States)

    Susheel Kumar, S. M.; Laxkar, Deepak; Adhikari, Sourav; Vijayarajan, V.

    2017-11-01

    Our work brings out comparison based on the performance of supervised machine learning algorithms on a binary classification task. The supervised machine learning algorithms which are taken into consideration in the following work are namely Support Vector Machine(SVM), Decision Tree(DT), K Nearest Neighbour (KNN), Naïve Bayes(NB) and Random Forest(RF). This paper mostly focuses on comparing the performance of above mentioned algorithms on one binary classification task by analysing the Metrics such as Accuracy, F-Measure, G-Measure, Precision, Misclassification Rate, False Positive Rate, True Positive Rate, Specificity, Prevalence.

  19. Learning semantic histopathological representation for basal cell carcinoma classification

    Science.gov (United States)

    Gutiérrez, Ricardo; Rueda, Andrea; Romero, Eduardo

    2013-03-01

    Diagnosis of a histopathology glass slide is a complex process that involves accurate recognition of several structures, their function in the tissue and their relation with other structures. The way in which the pathologist represents the image content and the relations between those objects yields a better and accurate diagnoses. Therefore, an appropriate semantic representation of the image content will be useful in several analysis tasks such as cancer classification, tissue retrieval and histopahological image analysis, among others. Nevertheless, to automatically recognize those structures and extract their inner semantic meaning are still very challenging tasks. In this paper we introduce a new semantic representation that allows to describe histopathological concepts suitable for classification. The approach herein identify local concepts using a dictionary learning approach, i.e., the algorithm learns the most representative atoms from a set of random sampled patches, and then models the spatial relations among them by counting the co-occurrence between atoms, while penalizing the spatial distance. The proposed approach was compared with a bag-of-features representation in a tissue classification task. For this purpose, 240 histological microscopical fields of view, 24 per tissue class, were collected. Those images fed a Support Vector Machine classifier per class, using 120 images as train set and the remaining ones for testing, maintaining the same proportion of each concept in the train and test sets. The obtained classification results, averaged from 100 random partitions of training and test sets, shows that our approach is more sensitive in average than the bag-of-features representation in almost 6%.

  20. Manifold regularized multitask feature learning for multimodality disease classification.

    Science.gov (United States)

    Jie, Biao; Zhang, Daoqiang; Cheng, Bo; Shen, Dinggang

    2015-02-01

    Multimodality based methods have shown great advantages in classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Recently, multitask feature selection methods are typically used for joint selection of common features across multiple modalities. However, one disadvantage of existing multimodality based methods is that they ignore the useful data distribution information in each modality, which is essential for subsequent classification. Accordingly, in this paper we propose a manifold regularized multitask feature learning method to preserve both the intrinsic relatedness among multiple modalities of data and the data distribution information in each modality. Specifically, we denote the feature learning on each modality as a single task, and use group-sparsity regularizer to capture the intrinsic relatedness among multiple tasks (i.e., modalities) and jointly select the common features from multiple tasks. Furthermore, we introduce a new manifold-based Laplacian regularizer to preserve the data distribution information from each task. Finally, we use the multikernel support vector machine method to fuse multimodality data for eventual classification. Conversely, we also extend our method to the semisupervised setting, where only partial data are labeled. We evaluate our method using the baseline magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), and cerebrospinal fluid (CSF) data of subjects from AD neuroimaging initiative database. The experimental results demonstrate that our proposed method can not only achieve improved classification performance, but also help to discover the disease-related brain regions useful for disease diagnosis. © 2014 Wiley Periodicals, Inc.

  1. Classification of nervous system withdrawn and approved drugs with ToxPrint features via machine learning strategies.

    Science.gov (United States)

    Onay, Aytun; Onay, Melih; Abul, Osman

    2017-04-01

    Early-phase virtual screening of candidate drug molecules plays a key role in pharmaceutical industry from data mining and machine learning to prevent adverse effects of the drugs. Computational classification methods can distinguish approved drugs from withdrawn ones. We focused on 6 data sets including maximum 110 approved and 110 withdrawn drugs for all and nervous system diseases to distinguish approved drugs from withdrawn ones. In this study, we used support vector machines (SVMs) and ensemble methods (EMs) such as boosted and bagged trees to classify drugs into approved and withdrawn categories. Also, we used CORINA Symphony program to identify Toxprint chemotypes including over 700 predefined chemotypes for determination of risk and safety assesment of candidate drug molecules. In addition, we studied nervous system withdrawn drugs to determine the key fragments with The ParMol package including gSpan algorithm. According to our results, the descriptors named as the number of total chemotypes and bond CN_amine_aliphatic_generic were more significant descriptors. The developed Medium Gaussian SVM model reached 78% prediction accuracy on test set for drug data set including all disease. Here, bagged tree and linear SVM models showed 89% of accuracies for phycholeptics and psychoanaleptics drugs. A set of discriminative fragments in nervous system withdrawn drug (NSWD) data sets was obtained. These fragments responsible for the drugs removed from market were benzene, toluene, N,N-dimethylethylamine, crotylamine, 5-methyl-2,4-heptadiene, octatriene and carbonyl group. This paper covers the development of computational classification methods to distinguish approved drugs from withdrawn ones. In addition, the results of this study indicated the identification of discriminative fragments is of significance to design a new nervous system approved drugs with interpretation of the structures of the NSWDs. Copyright © 2017 Elsevier B.V. All rights reserved.

  2. Comparative study of deep learning methods for one-shot image classification (abstract)

    NARCIS (Netherlands)

    van den Bogaert, J.; Mohseni, H.; Khodier, M.; Stoyanov, Y.; Mocanu, D.C.; Menkovski, V.

    2017-01-01

    Training deep learning models for images classification requires large amount of labeled data to overcome the challenges of overfitting and underfitting. Usually, in many practical applications, these labeled data are not available. In an attempt to solve this problem, the one-shot learning paradigm

  3. Pulmonary emphysema classification based on an improved texton learning model by sparse representation

    Science.gov (United States)

    Zhang, Min; Zhou, Xiangrong; Goshima, Satoshi; Chen, Huayue; Muramatsu, Chisako; Hara, Takeshi; Yokoyama, Ryujiro; Kanematsu, Masayuki; Fujita, Hiroshi

    2013-03-01

    In this paper, we present a texture classification method based on texton learned via sparse representation (SR) with new feature histogram maps in the classification of emphysema. First, an overcomplete dictionary of textons is learned via KSVD learning on every class image patches in the training dataset. In this stage, high-pass filter is introduced to exclude patches in smooth area to speed up the dictionary learning process. Second, 3D joint-SR coefficients and intensity histograms of the test images are used for characterizing regions of interest (ROIs) instead of conventional feature histograms constructed from SR coefficients of the test images over the dictionary. Classification is then performed using a classifier with distance as a histogram dissimilarity measure. Four hundreds and seventy annotated ROIs extracted from 14 test subjects, including 6 paraseptal emphysema (PSE) subjects, 5 centrilobular emphysema (CLE) subjects and 3 panlobular emphysema (PLE) subjects, are used to evaluate the effectiveness and robustness of the proposed method. The proposed method is tested on 167 PSE, 240 CLE and 63 PLE ROIs consisting of mild, moderate and severe pulmonary emphysema. The accuracy of the proposed system is around 74%, 88% and 89% for PSE, CLE and PLE, respectively.

  4. Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

    Science.gov (United States)

    Younghak Shin; Balasingham, Ilangko

    2017-07-01

    Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

  5. Classification and authentication of unknown water samples using machine learning algorithms.

    Science.gov (United States)

    Kundu, Palash K; Panchariya, P C; Kundu, Madhusree

    2011-07-01

    This paper proposes the development of water sample classification and authentication, in real life which is based on machine learning algorithms. The proposed techniques used experimental measurements from a pulse voltametry method which is based on an electronic tongue (E-tongue) instrumentation system with silver and platinum electrodes. E-tongue include arrays of solid state ion sensors, transducers even of different types, data collectors and data analysis tools, all oriented to the classification of liquid samples and authentication of unknown liquid samples. The time series signal and the corresponding raw data represent the measurement from a multi-sensor system. The E-tongue system, implemented in a laboratory environment for 6 numbers of different ISI (Bureau of Indian standard) certified water samples (Aquafina, Bisleri, Kingfisher, Oasis, Dolphin, and McDowell) was the data source for developing two types of machine learning algorithms like classification and regression. A water data set consisting of 6 numbers of sample classes containing 4402 numbers of features were considered. A PCA (principal component analysis) based classification and authentication tool was developed in this study as the machine learning component of the E-tongue system. A proposed partial least squares (PLS) based classifier, which was dedicated as well; to authenticate a specific category of water sample evolved out as an integral part of the E-tongue instrumentation system. The developed PCA and PLS based E-tongue system emancipated an overall encouraging authentication percentage accuracy with their excellent performances for the aforesaid categories of water samples. Copyright © 2011 ISA. Published by Elsevier Ltd. All rights reserved.

  6. Advanced Machine Learning for Classification, Regression, and Generation in Jet Physics

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    There is a deep connection between machine learning and jet physics - after all, jets are defined by unsupervised learning algorithms. Jet physics has been a driving force for studying modern machine learning in high energy physics. Domain specific challenges require new techniques to make full use of the algorithms. A key focus is on understanding how and what the algorithms learn. Modern machine learning techniques for jet physics are demonstrated for classification, regression, and generation. In addition to providing powerful baseline performance, we show how to train complex models directly on data and to generate sparse stacked images with non-uniform granularity.

  7. FCMPSO: An Imputation for Missing Data Features in Heart Disease Classification

    Science.gov (United States)

    Salleh, Mohd Najib Mohd; Ashikin Samat, Nurul

    2017-08-01

    The application of data mining and machine learning in directing clinical research into possible hidden knowledge is becoming greatly influential in medical areas. Heart Disease is a killer disease around the world, and early prevention through efficient methods can help to reduce the mortality number. Medical data may contain many uncertainties, as they are fuzzy and vague in nature. Nonetheless, imprecise features data such as no values and missing values can affect quality of classification results. Nevertheless, the other complete features are still capable to give information in certain features. Therefore, an imputation approach based on Fuzzy C-Means and Particle Swarm Optimization (FCMPSO) is developed in preprocessing stage to help fill in the missing values. Then, the complete dataset is trained in classification algorithm, Decision Tree. The experiment is trained with Heart Disease dataset and the performance is analysed using accuracy, precision, and ROC values. Results show that the performance of Decision Tree is increased after the application of FCMSPO for imputation.

  8. A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery Using a Probabilistic Learning Framework

    Science.gov (United States)

    Basu, Saikat; Ganguly, Sangram; Michaelis, Andrew; Votava, Petr; Roy, Anshuman; Mukhopadhyay, Supratik; Nemani, Ramakrishna

    2015-01-01

    Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets, which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

  9. A High Performance Computing Approach to Tree Cover Delineation in 1-m NAIP Imagery using a Probabilistic Learning Framework

    Science.gov (United States)

    Basu, S.; Ganguly, S.; Michaelis, A.; Votava, P.; Roy, A.; Mukhopadhyay, S.; Nemani, R. R.

    2015-12-01

    Tree cover delineation is a useful instrument in deriving Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) airborne imagery data. Numerous algorithms have been designed to address this problem, but most of them do not scale to these datasets which are of the order of terabytes. In this paper, we present a semi-automated probabilistic framework for the segmentation and classification of 1-m National Agriculture Imagery Program (NAIP) for tree-cover delineation for the whole of Continental United States, using a High Performance Computing Architecture. Classification is performed using a multi-layer Feedforward Backpropagation Neural Network and segmentation is performed using a Statistical Region Merging algorithm. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field, which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by relabeling misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the whole state of California, spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles. The framework produced true positive rates of around 88% for fragmented forests and 74% for urban tree cover areas, with false positive rates lower than 2% for both landscapes. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR canopy height model (CHM) showed the effectiveness of our framework for generating accurate high-resolution tree-cover maps.

  10. Visualizing Biological Data in Museums: Visitor Learning with an Interactive Tree of Life Exhibit

    Science.gov (United States)

    Horn, Michael S.; Phillips, Brenda C.; Evans, Evelyn Margaret; Block, Florian; Diamond, Judy; Shen, Chia

    2016-01-01

    In this study, we investigate museum visitor learning and engagement at an interactive visualization of an evolutionary tree of life consisting of over 70,000 species. The study was conducted at two natural history museums where visitors collaboratively explored the tree of life using direct touch gestures on a multi-touch tabletop display. In the…

  11. Modeling flash floods in ungauged mountain catchments of China: A decision tree learning approach for parameter regionalization

    Science.gov (United States)

    Ragettli, S.; Zhou, J.; Wang, H.; Liu, C.; Guo, L.

    2017-12-01

    Flash floods in small mountain catchments are one of the most frequent causes of loss of life and property from natural hazards in China. Hydrological models can be a useful tool for the anticipation of these events and the issuing of timely warnings. One of the main challenges of setting up such a system is finding appropriate model parameter values for ungauged catchments. Previous studies have shown that the transfer of parameter sets from hydrologically similar gauged catchments is one of the best performing regionalization methods. However, a remaining key issue is the identification of suitable descriptors of similarity. In this study, we use decision tree learning to explore parameter set transferability in the full space of catchment descriptors. For this purpose, a semi-distributed rainfall-runoff model is set up for 35 catchments in ten Chinese provinces. Hourly runoff data from in total 858 storm events are used to calibrate the model and to evaluate the performance of parameter set transfers between catchments. We then present a novel technique that uses the splitting rules of classification and regression trees (CART) for finding suitable donor catchments for ungauged target catchments. The ability of the model to detect flood events in assumed ungauged catchments is evaluated in series of leave-one-out tests. We show that CART analysis increases the probability of detection of 10-year flood events in comparison to a conventional measure of physiographic-climatic similarity by up to 20%. Decision tree learning can outperform other regionalization approaches because it generates rules that optimally consider spatial proximity and physical similarity. Spatial proximity can be used as a selection criteria but is skipped in the case where no similar gauged catchments are in the vicinity. We conclude that the CART regionalization concept is particularly suitable for implementation in sparsely gauged and topographically complex environments where a proximity

  12. Automatic plankton image classification combining multiple view features via multiple kernel learning.

    Science.gov (United States)

    Zheng, Haiyong; Wang, Ruchen; Yu, Zhibin; Wang, Nan; Gu, Zhaorui; Zheng, Bing

    2017-12-28

    Plankton, including phytoplankton and zooplankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, plankton is very sensitive to environment changes, and the study of plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoplankton to zooplankton. The experimental results validated that our system

  13. Categorizing ideas about trees: a tree of trees.

    Science.gov (United States)

    Fisler, Marie; Lecointre, Guillaume

    2013-01-01

    The aim of this study is to explore whether matrices and MP trees used to produce systematic categories of organisms could be useful to produce categories of ideas in history of science. We study the history of the use of trees in systematics to represent the diversity of life from 1766 to 1991. We apply to those ideas a method inspired from coding homologous parts of organisms. We discretize conceptual parts of ideas, writings and drawings about trees contained in 41 main writings; we detect shared parts among authors and code them into a 91-characters matrix and use a tree representation to show who shares what with whom. In other words, we propose a hierarchical representation of the shared ideas about trees among authors: this produces a "tree of trees." Then, we categorize schools of tree-representations. Classical schools like "cladists" and "pheneticists" are recovered but others are not: "gradists" are separated into two blocks, one of them being called here "grade theoreticians." We propose new interesting categories like the "buffonian school," the "metaphoricians," and those using "strictly genealogical classifications." We consider that networks are not useful to represent shared ideas at the present step of the study. A cladogram is made for showing who is sharing what with whom, but also heterobathmy and homoplasy of characters. The present cladogram is not modelling processes of transmission of ideas about trees, and here it is mostly used to test for proximity of ideas of the same age and for categorization.

  14. Integrating human and machine intelligence in galaxy morphology classification tasks

    Science.gov (United States)

    Beck, Melanie R.; Scarlata, Claudia; Fortson, Lucy F.; Lintott, Chris J.; Simmons, B. D.; Galloway, Melanie A.; Willett, Kyle W.; Dickinson, Hugh; Masters, Karen L.; Marshall, Philip J.; Wright, Darryl

    2018-06-01

    Quantifying galaxy morphology is a challenging yet scientifically rewarding task. As the scale of data continues to increase with upcoming surveys, traditional classification methods will struggle to handle the load. We present a solution through an integration of visual and automated classifications, preserving the best features of both human and machine. We demonstrate the effectiveness of such a system through a re-analysis of visual galaxy morphology classifications collected during the Galaxy Zoo 2 (GZ2) project. We reprocess the top-level question of the GZ2 decision tree with a Bayesian classification aggregation algorithm dubbed SWAP, originally developed for the Space Warps gravitational lens project. Through a simple binary classification scheme, we increase the classification rate nearly 5-fold classifying 226 124 galaxies in 92 d of GZ2 project time while reproducing labels derived from GZ2 classification data with 95.7 per cent accuracy. We next combine this with a Random Forest machine learning algorithm that learns on a suite of non-parametric morphology indicators widely used for automated morphologies. We develop a decision engine that delegates tasks between human and machine and demonstrate that the combined system provides at least a factor of 8 increase in the classification rate, classifying 210 803 galaxies in just 32 d of GZ2 project time with 93.1 per cent accuracy. As the Random Forest algorithm requires a minimal amount of computational cost, this result has important implications for galaxy morphology identification tasks in the era of Euclid and other large-scale surveys.

  15. Multi-Modal Curriculum Learning for Semi-Supervised Image Classification.

    Science.gov (United States)

    Gong, Chen; Tao, Dacheng; Maybank, Stephen J; Liu, Wei; Kang, Guoliang; Yang, Jie

    2016-07-01

    Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets.

  16. Semi-Supervised Learning for Classification of Protein Sequence Data

    Directory of Open Access Journals (Sweden)

    Brian R. King

    2008-01-01

    Full Text Available Protein sequence data continue to become available at an exponential rate. Annotation of functional and structural attributes of these data lags far behind, with only a small fraction of the data understood and labeled by experimental methods. Classification methods that are based on semi-supervised learning can increase the overall accuracy of classifying partly labeled data in many domains, but very few methods exist that have shown their effect on protein sequence classification. We show how proven methods from text classification can be applied to protein sequence data, as we consider both existing and novel extensions to the basic methods, and demonstrate restrictions and differences that must be considered. We demonstrate comparative results against the transductive support vector machine, and show superior results on the most difficult classification problems. Our results show that large repositories of unlabeled protein sequence data can indeed be used to improve predictive performance, particularly in situations where there are fewer labeled protein sequences available, and/or the data are highly unbalanced in nature.

  17. Representation Learning for Class C G Protein-Coupled Receptors Classification

    Directory of Open Access Journals (Sweden)

    Raúl Cruz-Barbosa

    2018-03-01

    Full Text Available G protein-coupled receptors (GPCRs are integral cell membrane proteins of relevance for pharmacology. The complete tertiary structure including both extracellular and transmembrane domains has not been determined for any member of class C GPCRs. An alternative way to work on GPCR structural models is the investigation of their functionality through the analysis of their primary structure. For this, sequence representation is a key factor for the GPCRs’ classification context, where usually, feature engineering is carried out. In this paper, we propose the use of representation learning to acquire the features that best represent the class C GPCR sequences and at the same time to obtain a model for classification automatically. Deep learning methods in conjunction with amino acid physicochemical property indices are then used for this purpose. Experimental results assessed by the classification accuracy, Matthews’ correlation coefficient and the balanced error rate show that using a hydrophobicity index and a restricted Boltzmann machine (RBM can achieve performance results (accuracy of 92.9% similar to those reported in the literature. As a second proposal, we combine two or more physicochemical property indices instead of only one as the input for a deep architecture in order to add information from the sequences. Experimental results show that using three hydrophobicity-related index combinations helps to improve the classification performance (accuracy of 94.1% of an RBM better than those reported in the literature for class C GPCRs without using feature selection methods.

  18. Robust Semi-Supervised Manifold Learning Algorithm for Classification

    Directory of Open Access Journals (Sweden)

    Mingxia Chen

    2018-01-01

    Full Text Available In the recent years, manifold learning methods have been widely used in data classification to tackle the curse of dimensionality problem, since they can discover the potential intrinsic low-dimensional structures of the high-dimensional data. Given partially labeled data, the semi-supervised manifold learning algorithms are proposed to predict the labels of the unlabeled points, taking into account label information. However, these semi-supervised manifold learning algorithms are not robust against noisy points, especially when the labeled data contain noise. In this paper, we propose a framework for robust semi-supervised manifold learning (RSSML to address this problem. The noisy levels of the labeled points are firstly predicted, and then a regularization term is constructed to reduce the impact of labeled points containing noise. A new robust semi-supervised optimization model is proposed by adding the regularization term to the traditional semi-supervised optimization model. Numerical experiments are given to show the improvement and efficiency of RSSML on noisy data sets.

  19. Machine Learning Based Localization and Classification with Atomic Magnetometers

    Science.gov (United States)

    Deans, Cameron; Griffin, Lewis D.; Marmugi, Luca; Renzoni, Ferruccio

    2018-01-01

    We demonstrate identification of position, material, orientation, and shape of objects imaged by a Rb 85 atomic magnetometer performing electromagnetic induction imaging supported by machine learning. Machine learning maximizes the information extracted from the images created by the magnetometer, demonstrating the use of hidden data. Localization 2.6 times better than the spatial resolution of the imaging system and successful classification up to 97% are obtained. This circumvents the need of solving the inverse problem and demonstrates the extension of machine learning to diffusive systems, such as low-frequency electrodynamics in media. Automated collection of task-relevant information from quantum-based electromagnetic imaging will have a relevant impact from biomedicine to security.

  20. Classification, (big) data analysis and statistical learning

    CERN Document Server

    Conversano, Claudio; Vichi, Maurizio

    2018-01-01

    This edited book focuses on the latest developments in classification, statistical learning, data analysis and related areas of data science, including statistical analysis of large datasets, big data analytics, time series clustering, integration of data from different sources, as well as social networks. It covers both methodological aspects as well as applications to a wide range of areas such as economics, marketing, education, social sciences, medicine, environmental sciences and the pharmaceutical industry. In addition, it describes the basic features of the software behind the data analysis results, and provides links to the corresponding codes and data sets where necessary. This book is intended for researchers and practitioners who are interested in the latest developments and applications in the field. The peer-reviewed contributions were presented at the 10th Scientific Meeting of the Classification and Data Analysis Group (CLADAG) of the Italian Statistical Society, held in Santa Margherita di Pul...

  1. Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification

    KAUST Repository

    Wang, Jim Jing-Yan

    2013-12-01

    Automated classification of tissue types of Region of Interest (ROI) in medical images has been an important application in Computer-Aided Diagnosis (CAD). Recently, bag-of-feature methods which treat each ROI as a set of local features have shown their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting the inner relationship between the visual words and their weights. To overcome this problem, we develop a novel algorithm, Joint-ViVo, which learns the vocabulary and visual word weights jointly. A unified objective function based on large margin is defined for learning of both visual vocabulary and visual word weights, and optimized alternately in the iterative algorithm. We test our algorithm on three tissue classification tasks: classifying breast tissue density in mammograms, classifying lung tissue in High-Resolution Computed Tomography (HRCT) images, and identifying brain tissue type in Magnetic Resonance Imaging (MRI). The results show that Joint-ViVo outperforms the state-of-art methods on tissue classification problems. © 2013 Elsevier Ltd.

  2. Optimized extreme learning machine for urban land cover classification using hyperspectral imagery

    Science.gov (United States)

    Su, Hongjun; Tian, Shufang; Cai, Yue; Sheng, Yehua; Chen, Chen; Najafian, Maryam

    2017-12-01

    This work presents a new urban land cover classification framework using the firefly algorithm (FA) optimized extreme learning machine (ELM). FA is adopted to optimize the regularization coefficient C and Gaussian kernel σ for kernel ELM. Additionally, effectiveness of spectral features derived from an FA-based band selection algorithm is studied for the proposed classification task. Three sets of hyperspectral databases were recorded using different sensors, namely HYDICE, HyMap, and AVIRIS. Our study shows that the proposed method outperforms traditional classification algorithms such as SVM and reduces computational cost significantly.

  3. AUTOMATIC TREE-CROWN DETECTION IN CHALLENGING SCENARIOS

    Directory of Open Access Journals (Sweden)

    D. Bulatov

    2016-06-01

    Full Text Available In this paper, a new procedure for individual tree detection and modeling is presented. The input of this procedure consists of a normalized digital surface model NDSM, and a possibly error-prone classification result. The procedure is modular so that the functionality, the advantages and the disadvantages for every single module will be explained. The most important technical contributions of the paper are: Employing watershed transformation combined with classification results, applying hotspots detectors for identifying treetops in groups of trees, and correcting NDSM by detecting and geometric reconstruction of small anomalies, such as earth walls. Two minor contributions are made up by a detailed literature research on available methods for individual tree detection and estimation of tree-crowns for clearly identified trees in order to reduce arbitrariness by assigning trees to one of the few types in the output model.

  4. Simulation-driven machine learning: Bearing fault classification

    Science.gov (United States)

    Sobie, Cameron; Freitas, Carina; Nicolai, Mike

    2018-01-01

    Increasing the accuracy of mechanical fault detection has the potential to improve system safety and economic performance by minimizing scheduled maintenance and the probability of unexpected system failure. Advances in computational performance have enabled the application of machine learning algorithms across numerous applications including condition monitoring and failure detection. Past applications of machine learning to physical failure have relied explicitly on historical data, which limits the feasibility of this approach to in-service components with extended service histories. Furthermore, recorded failure data is often only valid for the specific circumstances and components for which it was collected. This work directly addresses these challenges for roller bearings with race faults by generating training data using information gained from high resolution simulations of roller bearing dynamics, which is used to train machine learning algorithms that are then validated against four experimental datasets. Several different machine learning methodologies are compared starting from well-established statistical feature-based methods to convolutional neural networks, and a novel application of dynamic time warping (DTW) to bearing fault classification is proposed as a robust, parameter free method for race fault detection.

  5. Combining evolutionary algorithms with oblique decision trees to detect bent-double galaxies

    Science.gov (United States)

    Cantu-Paz, Erick; Kamath, Chandrika

    2000-10-01

    Decision tress have long been popular in classification as they use simple and easy-to-understand tests at each node. Most variants of decision trees test a single attribute at a node, leading to axis- parallel trees, where the test results in a hyperplane which is parallel to one of the dimensions in the attribute space. These trees can be rather large and inaccurate in cases where the concept to be learned is best approximated by oblique hyperplanes. In such cases, it may be more appropriate to use an oblique decision tree, where the decision at each node is a linear combination of the attributes. Oblique decision trees have not gained wide popularity in part due to the complexity of constructing good oblique splits and the tendency of existing splitting algorithms to get stuck in local minima. Several alternatives have been proposed to handle these problems including randomization in conjunction wiht deterministic hill-climbing and the use of simulated annealing. In this paper, we use evolutionary algorithms (EAs) to determine the split. EAs are well suited for this problem because of their global search properties, their tolerance to noisy fitness evaluations, and their scalability to large dimensional search spaces. We demonstrate our technique on a synthetic data set, and then we apply it to a practical problem from astronomy, namely, the classification of galaxies with a bent-double morphology. In addition, we describe our experiences with several split evaluation criteria. Our results suggest that, in some cases, the evolutionary approach is faster and more accurate than existing oblique decision tree algorithms. However, for our astronomical data, the accuracy is not significantly different than the axis-parallel trees.

  6. Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification

    OpenAIRE

    Zhang, Chenrui; Peng, Yuxin

    2018-01-01

    Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for feature learning via solving auxiliary tasks. However, existing methods in this regard suffer from two limitations when extended to video classification. First, they focus only on a single task, whereas ignoring complementarity among different task-specific feat...

  7. Classification of PolSAR Images Using Multilayer Autoencoders and a Self-Paced Learning Approach

    Directory of Open Access Journals (Sweden)

    Wenshuai Chen

    2018-01-01

    Full Text Available In this paper, a novel polarimetric synthetic aperture radar (PolSAR image classification method based on multilayer autoencoders and self-paced learning (SPL is proposed. The multilayer autoencoders network is used to learn the features, which convert raw data into more abstract expressions. Then, softmax regression is applied to produce the predicted probability distributions over all the classes of each pixel. When we optimize the multilayer autoencoders network, self-paced learning is used to accelerate the learning convergence and achieve a stronger generalization capability. Under this learning paradigm, the network learns the easier samples first and gradually involves more difficult samples in the training process. The proposed method achieves the overall classification accuracies of 94.73%, 94.82% and 78.12% on the Flevoland dataset from AIRSAR, Flevoland dataset from RADARSAT-2 and Yellow River delta dataset, respectively. Such results are comparable with other state-of-the-art methods.

  8. Multiple kernel learning using single stage function approximation for binary classification problems

    Science.gov (United States)

    Shiju, S.; Sumitra, S.

    2017-12-01

    In this paper, the multiple kernel learning (MKL) is formulated as a supervised classification problem. We dealt with binary classification data and hence the data modelling problem involves the computation of two decision boundaries of which one related with that of kernel learning and the other with that of input data. In our approach, they are found with the aid of a single cost function by constructing a global reproducing kernel Hilbert space (RKHS) as the direct sum of the RKHSs corresponding to the decision boundaries of kernel learning and input data and searching that function from the global RKHS, which can be represented as the direct sum of the decision boundaries under consideration. In our experimental analysis, the proposed model had shown superior performance in comparison with that of existing two stage function approximation formulation of MKL, where the decision functions of kernel learning and input data are found separately using two different cost functions. This is due to the fact that single stage representation helps the knowledge transfer between the computation procedures for finding the decision boundaries of kernel learning and input data, which inturn boosts the generalisation capacity of the model.

  9. Artificial Mangrove Species Mapping Using Pléiades-1: An Evaluation of Pixel-Based and Object-Based Classifications with Selected Machine Learning Algorithms

    Directory of Open Access Journals (Sweden)

    Dezhi Wang

    2018-02-01

    Full Text Available In the dwindling natural mangrove today, mangrove reforestation projects are conducted worldwide to prevent further losses. Due to monoculture and the low survival rate of artificial mangroves, it is necessary to pay attention to mapping and monitoring them dynamically. Remote sensing techniques have been widely used to map mangrove forests due to their capacity for large-scale, accurate, efficient, and repetitive monitoring. This study evaluated the capability of a 0.5-m Pléiades-1 in classifying artificial mangrove species using both pixel-based and object-based classification schemes. For comparison, three machine learning algorithms—decision tree (DT, support vector machine (SVM, and random forest (RF—were used as the classifiers in the pixel-based and object-based classification procedure. The results showed that both the pixel-based and object-based approaches could recognize the major discriminations between the four major artificial mangrove species. However, the object-based method had a better overall accuracy than the pixel-based method on average. For pixel-based image analysis, SVM produced the highest overall accuracy (79.63%; for object-based image analysis, RF could achieve the highest overall accuracy (82.40%, and it was also the best machine learning algorithm for classifying artificial mangroves. The patches produced by object-based image analysis approaches presented a more generalized appearance and could contiguously depict mangrove species communities. When the same machine learning algorithms were compared by McNemar’s test, a statistically significant difference in overall classification accuracy between the pixel-based and object-based classifications only existed in the RF algorithm. Regarding species, monoculture and dominant mangrove species Sonneratia apetala group 1 (SA1 as well as partly mixed and regular shape mangrove species Hibiscus tiliaceus (HT could well be identified. However, for complex and easily

  10. Optimizing tree-species classification in hyperspectal images

    CSIR Research Space (South Africa)

    Barnard, E

    2010-11-01

    Full Text Available for classification. Scaling of these components so that all features have equal variance is found to be useful, and their best performance (88.9% accurate classification) is achieved with 15 scaled features and a support vector machine as classifier. A graphical...

  11. IDOCS: intelligent distributed ontology consensus system--the use of machine learning in retinal drusen phenotyping.

    Science.gov (United States)

    Thomas, George; Grassi, Michael A; Lee, John R; Edwards, Albert O; Gorin, Michael B; Klein, Ronald; Casavant, Thomas L; Scheetz, Todd E; Stone, Edwin M; Williams, Andrew B

    2007-05-01

    To use the power of knowledge acquisition and machine learning in the development of a collaborative computer classification system based on the features of age-related macular degeneration (AMD). A vocabulary was acquired from four AMD experts who examined 100 ophthalmoscopic images. The vocabulary was analyzed, hierarchically structured, and incorporated into a collaborative computer classification system called IDOCS. Using this system, three of the experts examined images from a second set of digital images compiled from more than 1000 patients with AMD. Images were annotated, and features were identified and defined. Decision trees, a machine learning method, were trained on the data collected and used to extract patterns. Interrelationships between the data from the different clinicians were investigated. Six drusen classes in the structured vocabulary were largely sufficient to describe all the identified features. The decision trees classified the data with 76.86% to 88.5% accuracy and distilled patterns in the form of hierarchical trees composed of 5 to 15 nodes. Experts were largely consistent in their characterization of soft, and to a lesser extent, hard drusen, but diverge in definition of other drusen. Size and crystalline morphology were the main determinants of drusen type across all experts. Machine learning is a powerful tool for the characterization of disease phenotypes. The creation of a defined feature set for AMD will facilitate the development of an IDOCS-based classification system.

  12. A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series

    OpenAIRE

    Chambon, Stanislas; Galtier, Mathieu; Arnal, Pierrick; Wainrib, Gilles; Gramfort, Alexandre

    2017-01-01

    Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders. It is traditionally performed by a sleep expert who assigns to each 30s of signal a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEG), electrooculograms (EOG), electrocardiograms (ECG) and electromyograms (EMG). We introduce here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or...

  13. Accurate classification of brain gliomas by discriminate dictionary learning based on projective dictionary pair learning of proton magnetic resonance spectra.

    Science.gov (United States)

    Adebileje, Sikiru Afolabi; Ghasemi, Keyvan; Aiyelabegan, Hammed Tanimowo; Saligheh Rad, Hamidreza

    2017-04-01

    Proton magnetic resonance spectroscopy is a powerful noninvasive technique that complements the structural images of cMRI, which aids biomedical and clinical researches, by identifying and visualizing the compositions of various metabolites within the tissues of interest. However, accurate classification of proton magnetic resonance spectroscopy is still a challenging issue in clinics due to low signal-to-noise ratio, overlapping peaks of metabolites, and the presence of background macromolecules. This paper evaluates the performance of a discriminate dictionary learning classifiers based on projective dictionary pair learning method for brain gliomas proton magnetic resonance spectroscopy spectra classification task, and the result were compared with the sub-dictionary learning methods. The proton magnetic resonance spectroscopy data contain a total of 150 spectra (74 healthy, 23 grade II, 23 grade III, and 30 grade IV) from two databases. The datasets from both databases were first coupled together, followed by column normalization. The Kennard-Stone algorithm was used to split the datasets into its training and test sets. Performance comparison based on the overall accuracy, sensitivity, specificity, and precision was conducted. Based on the overall accuracy of our classification scheme, the dictionary pair learning method was found to outperform the sub-dictionary learning methods 97.78% compared with 68.89%, respectively. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

  14. Classification of Phishing Email Using Random Forest Machine Learning Technique

    Directory of Open Access Journals (Sweden)

    Andronicus A. Akinyelu

    2014-01-01

    Full Text Available Phishing is one of the major challenges faced by the world of e-commerce today. Thanks to phishing attacks, billions of dollars have been lost by many companies and individuals. In 2012, an online report put the loss due to phishing attack at about $1.5 billion. This global impact of phishing attacks will continue to be on the increase and thus requires more efficient phishing detection techniques to curb the menace. This paper investigates and reports the use of random forest machine learning algorithm in classification of phishing attacks, with the major objective of developing an improved phishing email classifier with better prediction accuracy and fewer numbers of features. From a dataset consisting of 2000 phishing and ham emails, a set of prominent phishing email features (identified from the literature were extracted and used by the machine learning algorithm with a resulting classification accuracy of 99.7% and low false negative (FN and false positive (FP rates.

  15. Voxel-based plaque classification in coronary intravascular optical coherence tomography images using decision trees

    Science.gov (United States)

    Kolluru, Chaitanya; Prabhu, David; Gharaibeh, Yazan; Wu, Hao; Wilson, David L.

    2018-02-01

    Intravascular Optical Coherence Tomography (IVOCT) is a high contrast, 3D microscopic imaging technique that can be used to assess atherosclerosis and guide stent interventions. Despite its advantages, IVOCT image interpretation is challenging and time consuming with over 500 image frames generated in a single pullback volume. We have developed a method to classify voxel plaque types in IVOCT images using machine learning. To train and test the classifier, we have used our unique database of labeled cadaver vessel IVOCT images accurately registered to gold standard cryoimages. This database currently contains 300 images and is growing. Each voxel is labeled as fibrotic, lipid-rich, calcified or other. Optical attenuation, intensity and texture features were extracted for each voxel and were used to build a decision tree classifier for multi-class classification. Five-fold cross-validation across images gave accuracies of 96 % +/- 0.01 %, 90 +/- 0.02% and 90 % +/- 0.01 % for fibrotic, lipid-rich and calcified classes respectively. To rectify performance degradation seen in left out vessel specimens as opposed to left out images, we are adding data and reducing features to limit overfitting. Following spatial noise cleaning, important vascular regions were unambiguous in display. We developed displays that enable physicians to make rapid determination of calcified and lipid regions. This will inform treatment decisions such as the need for devices (e.g., atherectomy or scoring balloon in the case of calcifications) or extended stent lengths to ensure coverage of lipid regions prone to injury at the edge of a stent.

  16. Optical beam classification using deep learning: a comparison with rule- and feature-based classification

    Science.gov (United States)

    Alom, Md. Zahangir; Awwal, Abdul A. S.; Lowe-Webb, Roger; Taha, Tarek M.

    2017-08-01

    Deep-learning methods are gaining popularity because of their state-of-the-art performance in image classification tasks. In this paper, we explore classification of laser-beam images from the National Ignition Facility (NIF) using a novel deeplearning approach. NIF is the world's largest, most energetic laser. It has nearly 40,000 optics that precisely guide, reflect, amplify, and focus 192 laser beams onto a fusion target. NIF utilizes four petawatt lasers called the Advanced Radiographic Capability (ARC) to produce backlighting X-ray illumination to capture implosion dynamics of NIF experiments with picosecond temporal resolution. In the current operational configuration, four independent short-pulse ARC beams are created and combined in a split-beam configuration in each of two NIF apertures at the entry of the pre-amplifier. The subaperture beams then propagate through the NIF beampath up to the ARC compressor. Each ARC beamlet is separately compressed with a dedicated set of four gratings and recombined as sub-apertures for transport to the parabola vessel, where the beams are focused using parabolic mirrors and pointed to the target. Small angular errors in the compressor gratings can cause the sub-aperture beams to diverge from one another and prevent accurate alignment through the transport section between the compressor and parabolic mirrors. This is an off-normal condition that must be detected and corrected. The goal of the off-normal check is to determine whether the ARC beamlets are sufficiently overlapped into a merged single spot or diverged into two distinct spots. Thus, the objective of the current work is three-fold: developing a simple algorithm to perform off-normal classification, exploring the use of Convolutional Neural Network (CNN) for the same task, and understanding the inter-relationship of the two approaches. The CNN recognition results are compared with other machine-learning approaches, such as Deep Neural Network (DNN) and Support

  17. Assessment and classification of hazardous street trees in University ...

    African Journals Online (AJOL)

    The study was carried out to assessed and classified hazardous trees within the University of Ibadan (UI) campus, Oyo State, Nigeria. The study population was 25 municipal tree species comprising of 420 individual trees located along the major roads of the study area, which were considered hazardous to the community.

  18. Deep transfer learning for automatic target classification: MWIR to LWIR

    Science.gov (United States)

    Ding, Zhengming; Nasrabadi, Nasser; Fu, Yun

    2016-05-01

    Publisher's Note: This paper, originally published on 5/12/2016, was replaced with a corrected/revised version on 5/18/2016. If you downloaded the original PDF but are unable to access the revision, please contact SPIE Digital Library Customer Service for assistance. When dealing with sparse or no labeled data in the target domain, transfer learning shows its appealing performance by borrowing the supervised knowledge from external domains. Recently deep structure learning has been exploited in transfer learning due to its attractive power in extracting effective knowledge through multi-layer strategy, so that deep transfer learning is promising to address the cross-domain mismatch. In general, cross-domain disparity can be resulted from the difference between source and target distributions or different modalities, e.g., Midwave IR (MWIR) and Longwave IR (LWIR). In this paper, we propose a Weighted Deep Transfer Learning framework for automatic target classification through a task-driven fashion. Specifically, deep features and classifier parameters are obtained simultaneously for optimal classification performance. In this way, the proposed deep structures can extract more effective features with the guidance of the classifier performance; on the other hand, the classifier performance is further improved since it is optimized on more discriminative features. Furthermore, we build a weighted scheme to couple source and target output by assigning pseudo labels to target data, therefore we can transfer knowledge from source (i.e., MWIR) to target (i.e., LWIR). Experimental results on real databases demonstrate the superiority of the proposed algorithm by comparing with others.

  19. Decision tree-based learning to predict patient controlled analgesia consumption and readjustment

    Directory of Open Access Journals (Sweden)

    Hu Yuh-Jyh

    2012-11-01

    Full Text Available Abstract Background Appropriate postoperative pain management contributes to earlier mobilization, shorter hospitalization, and reduced cost. The under treatment of pain may impede short-term recovery and have a detrimental long-term effect on health. This study focuses on Patient Controlled Analgesia (PCA, which is a delivery system for pain medication. This study proposes and demonstrates how to use machine learning and data mining techniques to predict analgesic requirements and PCA readjustment. Methods The sample in this study included 1099 patients. Every patient was described by 280 attributes, including the class attribute. In addition to commonly studied demographic and physiological factors, this study emphasizes attributes related to PCA. We used decision tree-based learning algorithms to predict analgesic consumption and PCA control readjustment based on the first few hours of PCA medications. We also developed a nearest neighbor-based data cleaning method to alleviate the class-imbalance problem in PCA setting readjustment prediction. Results The prediction accuracies of total analgesic consumption (continuous dose and PCA dose and PCA analgesic requirement (PCA dose only by an ensemble of decision trees were 80.9% and 73.1%, respectively. Decision tree-based learning outperformed Artificial Neural Network, Support Vector Machine, Random Forest, Rotation Forest, and Naïve Bayesian classifiers in analgesic consumption prediction. The proposed data cleaning method improved the performance of every learning method in this study of PCA setting readjustment prediction. Comparative analysis identified the informative attributes from the data mining models and compared them with the correlates of analgesic requirement reported in previous works. Conclusion This study presents a real-world application of data mining to anesthesiology. Unlike previous research, this study considers a wider variety of predictive factors, including PCA

  20. Remote sensing of aquatic vegetation distribution in Taihu Lake using an improved classification tree with modified thresholds.

    Science.gov (United States)

    Zhao, Dehua; Jiang, Hao; Yang, Tangwu; Cai, Ying; Xu, Delin; An, Shuqing

    2012-03-01

    Classification trees (CT) have been used successfully in the past to classify aquatic vegetation from spectral indices (SI) obtained from remotely-sensed images. However, applying CT models developed for certain image dates to other time periods within the same year or among different years can reduce the classification accuracy. In this study, we developed CT models with modified thresholds using extreme SI values (CT(m)) to improve the stability of the models when applying them to different time periods. A total of 903 ground-truth samples were obtained in September of 2009 and 2010 and classified as emergent, floating-leaf, or submerged vegetation or other cover types. Classification trees were developed for 2009 (Model-09) and 2010 (Model-10) using field samples and a combination of two images from winter and summer. Overall accuracies of these models were 92.8% and 94.9%, respectively, which confirmed the ability of CT analysis to map aquatic vegetation in Taihu Lake. However, Model-10 had only 58.9-71.6% classification accuracy and 31.1-58.3% agreement (i.e., pixels classified the same in the two maps) for aquatic vegetation when it was applied to image pairs from both a different time period in 2010 and a similar time period in 2009. We developed a method to estimate the effects of extrinsic (EF) and intrinsic (IF) factors on model uncertainty using Modis images. Results indicated that 71.1% of the instability in classification between time periods was due to EF, which might include changes in atmospheric conditions, sun-view angle and water quality. The remainder was due to IF, such as phenological and growth status differences between time periods. The modified version of Model-10 (i.e. CT(m)) performed better than traditional CT with different image dates. When applied to 2009 images, the CT(m) version of Model-10 had very similar thresholds and performance as Model-09, with overall accuracies of 92.8% and 90.5% for Model-09 and the CT(m) version of Model

  1. Test-Enhanced Learning of Natural Concepts: Effects on Recognition Memory, Classification, and Metacognition

    Science.gov (United States)

    Jacoby, Larry L.; Wahlheim, Christopher N.; Coane, Jennifer H.

    2010-01-01

    Three experiments examined testing effects on learning of natural concepts and metacognitive assessments of such learning. Results revealed that testing enhanced recognition memory and classification accuracy for studied and novel exemplars of bird families on immediate and delayed tests. These effects depended on the balance of study and test…

  2. Learning Word Embeddings with Chi-Square Weights for Healthcare Tweet Classification

    Directory of Open Access Journals (Sweden)

    Sicong Kuang

    2017-08-01

    Full Text Available Twitter is a popular source for the monitoring of healthcare information and public disease. However, there exists much noise in the tweets. Even though appropriate keywords appear in the tweets, they do not guarantee the identification of a truly health-related tweet. Thus, the traditional keyword-based classification task is largely ineffective. Algorithms for word embeddings have proved to be useful in many natural language processing (NLP tasks. We introduce two algorithms based on an existing word embedding learning algorithm: the continuous bag-of-words model (CBOW. We apply the proposed algorithms to the task of recognizing healthcare-related tweets. In the CBOW model, the vector representation of words is learned from their contexts. To simplify the computation, the context is represented by an average of all words inside the context window. However, not all words in the context window contribute equally to the prediction of the target word. Greedily incorporating all the words in the context window will largely limit the contribution of the useful semantic words and bring noisy or irrelevant words into the learning process, while existing word embedding algorithms also try to learn a weighted CBOW model. Their weights are based on existing pre-defined syntactic rules while ignoring the task of the learned embedding. We propose learning weights based on the words’ relative importance in the classification task. Our intuition is that such learned weights place more emphasis on words that have comparatively more to contribute to the later task. We evaluate the embeddings learned from our algorithms on two healthcare-related datasets. The experimental results demonstrate that embeddings learned from the proposed algorithms outperform existing techniques by a relative accuracy improvement of over 9%.

  3. Using classification tree modelling to investigate drug prescription practices at health facilities in rural Tanzania

    Directory of Open Access Journals (Sweden)

    Kajungu Dan K

    2012-09-01

    Full Text Available Abstract Background Drug prescription practices depend on several factors related to the patient, health worker and health facilities. A better understanding of the factors influencing prescription patterns is essential to develop strategies to mitigate the negative consequences associated with poor practices in both the public and private sectors. Methods A cross-sectional study was conducted in rural Tanzania among patients attending health facilities, and health workers. Patients, health workers and health facilities-related factors with the potential to influence drug prescription patterns were used to build a model of key predictors. Standard data mining methodology of classification tree analysis was used to define the importance of the different factors on prescription patterns. Results This analysis included 1,470 patients and 71 health workers practicing in 30 health facilities. Patients were mostly treated in dispensaries. Twenty two variables were used to construct two classification tree models: one for polypharmacy (prescription of ≥3 drugs on a single clinic visit and one for co-prescription of artemether-lumefantrine (AL with antibiotics. The most important predictor of polypharmacy was the diagnosis of several illnesses. Polypharmacy was also associated with little or no supervision of the health workers, administration of AL and private facilities. Co-prescription of AL with antibiotics was more frequent in children under five years of age and the other important predictors were transmission season, mode of diagnosis and the location of the health facility. Conclusion Standard data mining methodology is an easy-to-implement analytical approach that can be useful for decision-making. Polypharmacy is mainly due to the diagnosis of multiple illnesses.

  4. Learning Supervised Topic Models for Classification and Regression from Crowds

    DEFF Research Database (Denmark)

    Rodrigues, Filipe; Lourenco, Mariana; Ribeiro, Bernardete

    2017-01-01

    problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages...... annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression...

  5. Multi-pruning of decision trees for knowledge representation and classification

    KAUST Repository

    Azad, Mohammad

    2016-06-09

    We consider two important questions related to decision trees: first how to construct a decision tree with reasonable number of nodes and reasonable number of misclassification, and second how to improve the prediction accuracy of decision trees when they are used as classifiers. We have created a dynamic programming based approach for bi-criteria optimization of decision trees relative to the number of nodes and the number of misclassification. This approach allows us to construct the set of all Pareto optimal points and to derive, for each such point, decision trees with parameters corresponding to that point. Experiments on datasets from UCI ML Repository show that, very often, we can find a suitable Pareto optimal point and derive a decision tree with small number of nodes at the expense of small increment in number of misclassification. Based on the created approach we have proposed a multi-pruning procedure which constructs decision trees that, as classifiers, often outperform decision trees constructed by CART. © 2015 IEEE.

  6. Multi-pruning of decision trees for knowledge representation and classification

    KAUST Repository

    Azad, Mohammad; Chikalov, Igor; Hussain, Shahid; Moshkov, Mikhail

    2016-01-01

    We consider two important questions related to decision trees: first how to construct a decision tree with reasonable number of nodes and reasonable number of misclassification, and second how to improve the prediction accuracy of decision trees when they are used as classifiers. We have created a dynamic programming based approach for bi-criteria optimization of decision trees relative to the number of nodes and the number of misclassification. This approach allows us to construct the set of all Pareto optimal points and to derive, for each such point, decision trees with parameters corresponding to that point. Experiments on datasets from UCI ML Repository show that, very often, we can find a suitable Pareto optimal point and derive a decision tree with small number of nodes at the expense of small increment in number of misclassification. Based on the created approach we have proposed a multi-pruning procedure which constructs decision trees that, as classifiers, often outperform decision trees constructed by CART. © 2015 IEEE.

  7. Classification and learning using genetic algorithms applications in Bioinformatics and Web Intelligence

    CERN Document Server

    Bandyopadhyay, Sanghamitra

    2007-01-01

    This book provides a unified framework that describes how genetic learning can be used to design pattern recognition and learning systems. It examines how a search technique, the genetic algorithm, can be used for pattern classification mainly through approximating decision boundaries. Coverage also demonstrates the effectiveness of the genetic classifiers vis-à-vis several widely used classifiers, including neural networks.

  8. KLASIFIKASI KARAKTERISTIK KECELAKAAN LALU LINTAS DI KOTA DENPASAR DENGAN PENDEKATAN CLASSIFICATION AND REGRESSION TREES (CART

    Directory of Open Access Journals (Sweden)

    I GEDE AGUS JIWADIANA

    2015-11-01

    Full Text Available The aim of this research is to determine the classification characteristics of traffic accidents in Denpasar city in January-July 2014 by using Classification And Regression Trees (CART. Then, for determine the explanatory variables into the main classifier of CART. The result showed that optimum CART generate three terminal node. First terminal node, there are 12 people were classified as heavy traffic accident characteritics with single accident, and second terminal nodes, there are 68 people were classified as minor traffic accident characteristics by type of traffic accident front-rear, front-front, front-side, pedestrians, side-side and location of traffic accident in district road and sub-district road. For third terminal node, there are 291 people were classified as medium traffic accident characteristics by type of traffic accident front-rear, front-front, front-side, pedestrians, side-side and location of traffic accident in municipality road and explanatory variables into the main splitter to make of CART is type of traffic accident with maximum homogeneity measure of 0.03252.

  9. Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.

    Science.gov (United States)

    Ranjith, G; Parvathy, R; Vikas, V; Chandrasekharan, Kesavadas; Nair, Suresh

    2015-04-01

    With the advent of new imaging modalities, radiologists are faced with handling increasing volumes of data for diagnosis and treatment planning. The use of automated and intelligent systems is becoming essential in such a scenario. Machine learning, a branch of artificial intelligence, is increasingly being used in medical image analysis applications such as image segmentation, registration and computer-aided diagnosis and detection. Histopathological analysis is currently the gold standard for classification of brain tumors. The use of machine learning algorithms along with extraction of relevant features from magnetic resonance imaging (MRI) holds promise of replacing conventional invasive methods of tumor classification. The aim of the study is to classify gliomas into benign and malignant types using MRI data. Retrospective data from 28 patients who were diagnosed with glioma were used for the analysis. WHO Grade II (low-grade astrocytoma) was classified as benign while Grade III (anaplastic astrocytoma) and Grade IV (glioblastoma multiforme) were classified as malignant. Features were extracted from MR spectroscopy. The classification was done using four machine learning algorithms: multilayer perceptrons, support vector machine, random forest and locally weighted learning. Three of the four machine learning algorithms gave an area under ROC curve in excess of 0.80. Random forest gave the best performance in terms of AUC (0.911) while sensitivity was best for locally weighted learning (86.1%). The performance of different machine learning algorithms in the classification of gliomas is promising. An even better performance may be expected by integrating features extracted from other MR sequences. © The Author(s) 2015 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

  10. Human action analysis with randomized trees

    CERN Document Server

    Yu, Gang; Liu, Zicheng

    2014-01-01

    This book will provide a comprehensive overview on human action analysis with randomized trees. It will cover both the supervised random trees and the unsupervised random trees. When there are sufficient amount of labeled data available, supervised random trees provides a fast method for space-time interest point matching. When labeled data is minimal as in the case of example-based action search, unsupervised random trees is used to leverage the unlabelled data. We describe how the randomized trees can be used for action classification, action detection, action search, and action prediction.

  11. Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification

    Directory of Open Access Journals (Sweden)

    Qingshan Liu

    2017-12-01

    Full Text Available This paper proposes a novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM network to automatically learn the spectral-spatial features from hyperspectral images (HSIs. In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it. Meanwhile, inspired from the widely used convolutional neural network (CNN, a convolution operator across the spatial domain is incorporated into the network to extract the spatial feature. In addition, to sufficiently capture the spectral information, a bidirectional recurrent connection is proposed. In the classification phase, the learned features are concatenated into a vector and fed to a Softmax classifier via a fully-connected operator. To validate the effectiveness of the proposed Bi-CLSTM framework, we compare it with six state-of-the-art methods, including the popular 3D-CNN model, on three widely used HSIs (i.e., Indian Pines, Pavia University, and Kennedy Space Center. The obtained results show that Bi-CLSTM can improve the classification performance by almost 1.5 % as compared to 3D-CNN.

  12. An application to pulmonary emphysema classification based on model of texton learning by sparse representation

    Science.gov (United States)

    Zhang, Min; Zhou, Xiangrong; Goshima, Satoshi; Chen, Huayue; Muramatsu, Chisako; Hara, Takeshi; Yokoyama, Ryojiro; Kanematsu, Masayuki; Fujita, Hiroshi

    2012-03-01

    We aim at using a new texton based texture classification method in the classification of pulmonary emphysema in computed tomography (CT) images of the lungs. Different from conventional computer-aided diagnosis (CAD) pulmonary emphysema classification methods, in this paper, firstly, the dictionary of texton is learned via applying sparse representation(SR) to image patches in the training dataset. Then the SR coefficients of the test images over the dictionary are used to construct the histograms for texture presentations. Finally, classification is performed by using a nearest neighbor classifier with a histogram dissimilarity measure as distance. The proposed approach is tested on 3840 annotated regions of interest consisting of normal tissue and mild, moderate and severe pulmonary emphysema of three subtypes. The performance of the proposed system, with an accuracy of about 88%, is comparably higher than state of the art method based on the basic rotation invariant local binary pattern histograms and the texture classification method based on texton learning by k-means, which performs almost the best among other approaches in the literature.

  13. Toward optimal feature selection using ranking methods and classification algorithms

    Directory of Open Access Journals (Sweden)

    Novaković Jasmina

    2011-01-01

    Full Text Available We presented a comparison between several feature ranking methods used on two real datasets. We considered six ranking methods that can be divided into two broad categories: statistical and entropy-based. Four supervised learning algorithms are adopted to build models, namely, IB1, Naive Bayes, C4.5 decision tree and the RBF network. We showed that the selection of ranking methods could be important for classification accuracy. In our experiments, ranking methods with different supervised learning algorithms give quite different results for balanced accuracy. Our cases confirm that, in order to be sure that a subset of features giving the highest accuracy has been selected, the use of many different indices is recommended.

  14. An assessment of support vector machines for land cover classification

    Science.gov (United States)

    Huang, C.; Davis, L.S.; Townshend, J.R.G.

    2002-01-01

    The support vector machine (SVM) is a group of theoretically superior machine learning algorithms. It was found competitive with the best available machine learning algorithms in classifying high-dimensional data sets. This paper gives an introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classifications from satellite images. The SVM was compared to three other popular classifiers, including the maximum likelihood classifier (MLC), neural network classifiers (NNC) and decision tree classifiers (DTC). The impacts of kernel configuration on the performance of the SVM and of the selection of training data and input variables on the four classifiers were also evaluated in this experiment.

  15. Prototype-based Models for the Supervised Learning of Classification Schemes

    Science.gov (United States)

    Biehl, Michael; Hammer, Barbara; Villmann, Thomas

    2017-06-01

    An introduction is given to the use of prototype-based models in supervised machine learning. The main concept of the framework is to represent previously observed data in terms of so-called prototypes, which reflect typical properties of the data. Together with a suitable, discriminative distance or dissimilarity measure, prototypes can be used for the classification of complex, possibly high-dimensional data. We illustrate the framework in terms of the popular Learning Vector Quantization (LVQ). Most frequently, standard Euclidean distance is employed as a distance measure. We discuss how LVQ can be equipped with more general dissimilarites. Moreover, we introduce relevance learning as a tool for the data-driven optimization of parameterized distances.

  16. Classification algorithms using adaptive partitioning

    KAUST Repository

    Binev, Peter; Cohen, Albert; Dahmen, Wolfgang; DeVore, Ronald

    2014-01-01

    © 2014 Institute of Mathematical Statistics. Algorithms for binary classification based on adaptive tree partitioning are formulated and analyzed for both their risk performance and their friendliness to numerical implementation. The algorithms can be viewed as generating a set approximation to the Bayes set and thus fall into the general category of set estimators. In contrast with the most studied tree-based algorithms, which utilize piecewise constant approximation on the generated partition [IEEE Trans. Inform. Theory 52 (2006) 1335.1353; Mach. Learn. 66 (2007) 209.242], we consider decorated trees, which allow us to derive higher order methods. Convergence rates for these methods are derived in terms the parameter - of margin conditions and a rate s of best approximation of the Bayes set by decorated adaptive partitions. They can also be expressed in terms of the Besov smoothness β of the regression function that governs its approximability by piecewise polynomials on adaptive partition. The execution of the algorithms does not require knowledge of the smoothness or margin conditions. Besov smoothness conditions are weaker than the commonly used Holder conditions, which govern approximation by nonadaptive partitions, and therefore for a given regression function can result in a higher rate of convergence. This in turn mitigates the compatibility conflict between smoothness and margin parameters.

  17. Classification algorithms using adaptive partitioning

    KAUST Repository

    Binev, Peter

    2014-12-01

    © 2014 Institute of Mathematical Statistics. Algorithms for binary classification based on adaptive tree partitioning are formulated and analyzed for both their risk performance and their friendliness to numerical implementation. The algorithms can be viewed as generating a set approximation to the Bayes set and thus fall into the general category of set estimators. In contrast with the most studied tree-based algorithms, which utilize piecewise constant approximation on the generated partition [IEEE Trans. Inform. Theory 52 (2006) 1335.1353; Mach. Learn. 66 (2007) 209.242], we consider decorated trees, which allow us to derive higher order methods. Convergence rates for these methods are derived in terms the parameter - of margin conditions and a rate s of best approximation of the Bayes set by decorated adaptive partitions. They can also be expressed in terms of the Besov smoothness β of the regression function that governs its approximability by piecewise polynomials on adaptive partition. The execution of the algorithms does not require knowledge of the smoothness or margin conditions. Besov smoothness conditions are weaker than the commonly used Holder conditions, which govern approximation by nonadaptive partitions, and therefore for a given regression function can result in a higher rate of convergence. This in turn mitigates the compatibility conflict between smoothness and margin parameters.

  18. A comparison of machine learning algorithms for chemical toxicity classification using a simulated multi-scale data model

    Directory of Open Access Journals (Sweden)

    Li Zhen

    2008-05-01

    Full Text Available Abstract Background Bioactivity profiling using high-throughput in vitro assays can reduce the cost and time required for toxicological screening of environmental chemicals and can also reduce the need for animal testing. Several public efforts are aimed at discovering patterns or classifiers in high-dimensional bioactivity space that predict tissue, organ or whole animal toxicological endpoints. Supervised machine learning is a powerful approach to discover combinatorial relationships in complex in vitro/in vivo datasets. We present a novel model to simulate complex chemical-toxicology data sets and use this model to evaluate the relative performance of different machine learning (ML methods. Results The classification performance of Artificial Neural Networks (ANN, K-Nearest Neighbors (KNN, Linear Discriminant Analysis (LDA, Naïve Bayes (NB, Recursive Partitioning and Regression Trees (RPART, and Support Vector Machines (SVM in the presence and absence of filter-based feature selection was analyzed using K-way cross-validation testing and independent validation on simulated in vitro assay data sets with varying levels of model complexity, number of irrelevant features and measurement noise. While the prediction accuracy of all ML methods decreased as non-causal (irrelevant features were added, some ML methods performed better than others. In the limit of using a large number of features, ANN and SVM were always in the top performing set of methods while RPART and KNN (k = 5 were always in the poorest performing set. The addition of measurement noise and irrelevant features decreased the classification accuracy of all ML methods, with LDA suffering the greatest performance degradation. LDA performance is especially sensitive to the use of feature selection. Filter-based feature selection generally improved performance, most strikingly for LDA. Conclusion We have developed a novel simulation model to evaluate machine learning methods for the

  19. Rough Sets as a Knowledge Discovery and Classification Tool for the Diagnosis of Students with Learning Disabilities

    Directory of Open Access Journals (Sweden)

    Yu-Chi Lin

    2011-02-01

    Full Text Available Due to the implicit characteristics of learning disabilities (LDs, the diagnosis of students with learning disabilities has long been a difficult issue. Artificial intelligence techniques like artificial neural network (ANN and support vector machine (SVM have been applied to the LD diagnosis problem with satisfactory outcomes. However, special education teachers or professionals tend to be skeptical to these kinds of black-box predictors. In this study, we adopt the rough set theory (RST, which can not only perform as a classifier, but may also produce meaningful explanations or rules, to the LD diagnosis application. Our experiments indicate that the RST approach is competitive as a tool for feature selection, and it performs better in term of prediction accuracy than other rulebased algorithms such as decision tree and ripper algorithms. We also propose to mix samples collected from sources with different LD diagnosis procedure and criteria. By pre-processing these mixed samples with simple and readily available clustering algorithms, we are able to improve the quality and support of rules generated by the RST. Overall, our study shows that the rough set approach, as a classification and knowledge discovery tool, may have great potential in playing an essential role in LD diagnosis.

  20. Cosmic String Detection with Tree-Based Machine Learning

    Science.gov (United States)

    Vafaei Sadr, A.; Farhang, M.; Movahed, S. M. S.; Bassett, B.; Kunz, M.

    2018-05-01

    We explore the use of random forest and gradient boosting, two powerful tree-based machine learning algorithms, for the detection of cosmic strings in maps of the cosmic microwave background (CMB), through their unique Gott-Kaiser-Stebbins effect on the temperature anisotropies. The information in the maps is compressed into feature vectors before being passed to the learning units. The feature vectors contain various statistical measures of the processed CMB maps that boost cosmic string detectability. Our proposed classifiers, after training, give results similar to or better than claimed detectability levels from other methods for string tension, Gμ. They can make 3σ detection of strings with Gμ ≳ 2.1 × 10-10 for noise-free, 0.9΄-resolution CMB observations. The minimum detectable tension increases to Gμ ≳ 3.0 × 10-8 for a more realistic, CMB S4-like (II) strategy, improving over previous results.

  1. Machine Learning Techniques for Stellar Light Curve Classification

    Science.gov (United States)

    Hinners, Trisha A.; Tat, Kevin; Thorp, Rachel

    2018-07-01

    We apply machine learning techniques in an attempt to predict and classify stellar properties from noisy and sparse time-series data. We preprocessed over 94 GB of Kepler light curves from the Mikulski Archive for Space Telescopes (MAST) to classify according to 10 distinct physical properties using both representation learning and feature engineering approaches. Studies using machine learning in the field have been primarily done on simulated data, making our study one of the first to use real light-curve data for machine learning approaches. We tuned our data using previous work with simulated data as a template and achieved mixed results between the two approaches. Representation learning using a long short-term memory recurrent neural network produced no successful predictions, but our work with feature engineering was successful for both classification and regression. In particular, we were able to achieve values for stellar density, stellar radius, and effective temperature with low error (∼2%–4%) and good accuracy (∼75%) for classifying the number of transits for a given star. The results show promise for improvement for both approaches upon using larger data sets with a larger minority class. This work has the potential to provide a foundation for future tools and techniques to aid in the analysis of astrophysical data.

  2. An Active Learning Classifier for Further Reducing Diabetic Retinopathy Screening System Cost

    Directory of Open Access Journals (Sweden)

    Yinan Zhang

    2016-01-01

    Full Text Available Diabetic retinopathy (DR screening system raises a financial problem. For further reducing DR screening cost, an active learning classifier is proposed in this paper. Our approach identifies retinal images based on features extracted by anatomical part recognition and lesion detection algorithms. Kernel extreme learning machine (KELM is a rapid classifier for solving classification problems in high dimensional space. Both active learning and ensemble technique elevate performance of KELM when using small training dataset. The committee only proposes necessary manual work to doctor for saving cost. On the publicly available Messidor database, our classifier is trained with 20%–35% of labeled retinal images and comparative classifiers are trained with 80% of labeled retinal images. Results show that our classifier can achieve better classification accuracy than Classification and Regression Tree, radial basis function SVM, Multilayer Perceptron SVM, Linear SVM, and K Nearest Neighbor. Empirical experiments suggest that our active learning classifier is efficient for further reducing DR screening cost.

  3. Groundwater level prediction of landslide based on classification and regression tree

    Directory of Open Access Journals (Sweden)

    Yannan Zhao

    2016-09-01

    Full Text Available According to groundwater level monitoring data of Shuping landslide in the Three Gorges Reservoir area, based on the response relationship between influential factors such as rainfall and reservoir level and the change of groundwater level, the influential factors of groundwater level were selected. Then the classification and regression tree (CART model was constructed by the subset and used to predict the groundwater level. Through the verification, the predictive results of the test sample were consistent with the actually measured values, and the mean absolute error and relative error is 0.28 m and 1.15% respectively. To compare the support vector machine (SVM model constructed using the same set of factors, the mean absolute error and relative error of predicted results is 1.53 m and 6.11% respectively. It is indicated that CART model has not only better fitting and generalization ability, but also strong advantages in the analysis of landslide groundwater dynamic characteristics and the screening of important variables. It is an effective method for prediction of ground water level in landslides.

  4. Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

    Science.gov (United States)

    Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

    2015-10-30

    Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.

  5. Multimodal Task-Driven Dictionary Learning for Image Classification

    Science.gov (United States)

    2015-12-18

    recognition, multi-view face recognition, multi-view action recognition, and multimodal biometric recognition. It is also shown that, compared to the...improvement in several multi-task learning applications such as target classification, biometric recognitions, and multiview face recognition [12], [14], [17...relevant samples from other modalities for a given unimodal query. However, α1 α2 …αS D1 … Index finger Thumb finger … Iris x1 x2 xS D2 DS … … … J o in

  6. Research into Financial Position of Listed Companies following Classification via Extreme Learning Machine Based upon DE Optimization

    Directory of Open Access Journals (Sweden)

    Fu Yu

    2016-01-01

    Full Text Available By means of the model of extreme learning machine based upon DE optimization, this article particularly centers on the optimization thinking of such a model as well as its application effect in the field of listed company’s financial position classification. It proves that the improved extreme learning machine algorithm based upon DE optimization eclipses the traditional extreme learning machine algorithm following comparison. Meanwhile, this article also intends to introduce certain research thinking concerning extreme learning machine into the economics classification area so as to fulfill the purpose of computerizing the speedy but effective evaluation of massive financial statements of listed companies pertain to different classes

  7. Proactive data mining with decision trees

    CERN Document Server

    Dahan, Haim; Rokach, Lior; Maimon, Oded

    2014-01-01

    This book explores a proactive and domain-driven method to classification tasks. This novel proactive approach to data mining not only induces a model for predicting or explaining a phenomenon, but also utilizes specific problem/domain knowledge to suggest specific actions to achieve optimal changes in the value of the target attribute. In particular, the authors suggest a specific implementation of the domain-driven proactive approach for classification trees. The book centers on the core idea of moving observations from one branch of the tree to another. It introduces a novel splitting crite

  8. Deep learning for hybrid EEG-fNIRS brain–computer interface: application to motor imagery classification

    Science.gov (United States)

    Chiarelli, Antonio Maria; Croce, Pierpaolo; Merla, Arcangelo; Zappasodi, Filippo

    2018-06-01

    Objective. Brain–computer interface (BCI) refers to procedures that link the central nervous system to a device. BCI was historically performed using electroencephalography (EEG). In the last years, encouraging results were obtained by combining EEG with other neuroimaging technologies, such as functional near infrared spectroscopy (fNIRS). A crucial step of BCI is brain state classification from recorded signal features. Deep artificial neural networks (DNNs) recently reached unprecedented complex classification outcomes. These performances were achieved through increased computational power, efficient learning algorithms, valuable activation functions, and restricted or back-fed neurons connections. By expecting significant overall BCI performances, we investigated the capabilities of combining EEG and fNIRS recordings with state-of-the-art deep learning procedures. Approach. We performed a guided left and right hand motor imagery task on 15 subjects with a fixed classification response time of 1 s and overall experiment length of 10 min. Left versus right classification accuracy of a DNN in the multi-modal recording modality was estimated and it was compared to standalone EEG and fNIRS and other classifiers. Main results. At a group level we obtained significant increase in performance when considering multi-modal recordings and DNN classifier with synergistic effect. Significance. BCI performances can be significantly improved by employing multi-modal recordings that provide electrical and hemodynamic brain activity information, in combination with advanced non-linear deep learning classification procedures.

  9. Brake fault diagnosis using Clonal Selection Classification Algorithm (CSCA – A statistical learning approach

    Directory of Open Access Journals (Sweden)

    R. Jegadeeshwaran

    2015-03-01

    Full Text Available In automobile, brake system is an essential part responsible for control of the vehicle. Any failure in the brake system impacts the vehicle's motion. It will generate frequent catastrophic effects on the vehicle cum passenger's safety. Thus the brake system plays a vital role in an automobile and hence condition monitoring of the brake system is essential. Vibration based condition monitoring using machine learning techniques are gaining momentum. This study is one such attempt to perform the condition monitoring of a hydraulic brake system through vibration analysis. In this research, the performance of a Clonal Selection Classification Algorithm (CSCA for brake fault diagnosis has been reported. A hydraulic brake system test rig was fabricated. Under good and faulty conditions of a brake system, the vibration signals were acquired using a piezoelectric transducer. The statistical parameters were extracted from the vibration signal. The best feature set was identified for classification using attribute evaluator. The selected features were then classified using CSCA. The classification accuracy of such artificial intelligence technique has been compared with other machine learning approaches and discussed. The Clonal Selection Classification Algorithm performs better and gives the maximum classification accuracy (96% for the fault diagnosis of a hydraulic brake system.

  10. Polarimetric SAR Image Classification Using Multiple-feature Fusion and Ensemble Learning

    Directory of Open Access Journals (Sweden)

    Sun Xun

    2016-12-01

    Full Text Available In this paper, we propose a supervised classification algorithm for Polarimetric Synthetic Aperture Radar (PolSAR images using multiple-feature fusion and ensemble learning. First, we extract different polarimetric features, including extended polarimetric feature space, Hoekman, Huynen, H/alpha/A, and fourcomponent scattering features of PolSAR images. Next, we randomly select two types of features each time from all feature sets to guarantee the reliability and diversity of later ensembles and use a support vector machine as the basic classifier for predicting classification results. Finally, we concatenate all prediction probabilities of basic classifiers as the final feature representation and employ the random forest method to obtain final classification results. Experimental results at the pixel and region levels show the effectiveness of the proposed algorithm.

  11. A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification.

    Science.gov (United States)

    Peikari, Mohammad; Salama, Sherine; Nofech-Mozes, Sharon; Martel, Anne L

    2018-05-08

    Completely labeled pathology datasets are often challenging and time-consuming to obtain. Semi-supervised learning (SSL) methods are able to learn from fewer labeled data points with the help of a large number of unlabeled data points. In this paper, we investigated the possibility of using clustering analysis to identify the underlying structure of the data space for SSL. A cluster-then-label method was proposed to identify high-density regions in the data space which were then used to help a supervised SVM in finding the decision boundary. We have compared our method with other supervised and semi-supervised state-of-the-art techniques using two different classification tasks applied to breast pathology datasets. We found that compared with other state-of-the-art supervised and semi-supervised methods, our SSL method is able to improve classification performance when a limited number of labeled data instances are made available. We also showed that it is important to examine the underlying distribution of the data space before applying SSL techniques to ensure semi-supervised learning assumptions are not violated by the data.

  12. Land Cover and Land Use Classification with TWOPAC: towards Automated Processing for Pixel- and Object-Based Image Classification

    Directory of Open Access Journals (Sweden)

    Stefan Dech

    2012-09-01

    Full Text Available We present a novel and innovative automated processing environment for the derivation of land cover (LC and land use (LU information. This processing framework named TWOPAC (TWinned Object and Pixel based Automated classification Chain enables the standardized, independent, user-friendly, and comparable derivation of LC and LU information, with minimized manual classification labor. TWOPAC allows classification of multi-spectral and multi-temporal remote sensing imagery from different sensor types. TWOPAC enables not only pixel-based classification, but also allows classification based on object-based characteristics. Classification is based on a Decision Tree approach (DT for which the well-known C5.0 code has been implemented, which builds decision trees based on the concept of information entropy. TWOPAC enables automatic generation of the decision tree classifier based on a C5.0-retrieved ascii-file, as well as fully automatic validation of the classification output via sample based accuracy assessment.Envisaging the automated generation of standardized land cover products, as well as area-wide classification of large amounts of data in preferably a short processing time, standardized interfaces for process control, Web Processing Services (WPS, as introduced by the Open Geospatial Consortium (OGC, are utilized. TWOPAC’s functionality to process geospatial raster or vector data via web resources (server, network enables TWOPAC’s usability independent of any commercial client or desktop software and allows for large scale data processing on servers. Furthermore, the components of TWOPAC were built-up using open source code components and are implemented as a plug-in for Quantum GIS software for easy handling of the classification process from the user’s perspective.

  13. BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

    Science.gov (United States)

    Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

    2018-04-11

    The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes

  14. Profiling Student Use of Calculators in the Learning of High School Mathematics

    Science.gov (United States)

    Crowe, Cheryll E.; Ma, Xin

    2010-01-01

    Using data from the 2005 National Assessment of Educational Progress, students' use of calculators in the learning of high school mathematics was profiled based on their family background, curriculum background, and advanced mathematics coursework. A statistical method new to educational research--classification and regression trees--was applied…

  15. Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

    Science.gov (United States)

    Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

    2003-01-01

    Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

  16. A Proposed Functional Abilities Classification Tool for Developmental Disorders Affecting Learning and Behaviour

    Directory of Open Access Journals (Sweden)

    Benjamin Klein

    2018-02-01

    Full Text Available Children with developmental disorders affecting learning and behaviour (DDALB (e.g., attention, social communication, language, and learning disabilities, etc. require individualized support across multiple environments to promote participation, quality of life, and developmental outcomes. Support to enhance participation is based largely on individual profiles of functioning (e.g., communication, cognitive, social skills, executive functioning, etc., which are highly heterogeneous within medical diagnoses. Currently educators, clinicians, and parents encounter widespread difficulties in meeting children’s needs as there is lack of universal classification of functioning and disability for use in school environments. Objective: a practical tool for functional classification broadly applicable for children with DDALB could facilitate the collaboration, identification of points of entry of support, individual program planning, and reassessment in a transparent, equitable process based on functional need and context. We propose such a tool, the Functional Abilities Classification Tool (FACT based on the concepts of the ICF (International Classification of Functioning, Disability and Health. FACT is intended to provide ability and participation classification that is complementary to medical diagnosis. For children presenting with difficulties, the proposed tool initially classifies participation over several environments. Then, functional abilities are classified and personal factors and environment are described. Points of entry for support are identified given an analysis of functional ability profile, personal factors, environmental features, and pattern of participation. Conclusion: case examples, use of the tool and implications for children, agencies, and the system are described.

  17. Exploring diversity in ensemble classification: Applications in large area land cover mapping

    Science.gov (United States)

    Mellor, Andrew; Boukir, Samia

    2017-07-01

    Ensemble classifiers, such as random forests, are now commonly applied in the field of remote sensing, and have been shown to perform better than single classifier systems, resulting in reduced generalisation error. Diversity across the members of ensemble classifiers is known to have a strong influence on classification performance - whereby classifier errors are uncorrelated and more uniformly distributed across ensemble members. The relationship between ensemble diversity and classification performance has not yet been fully explored in the fields of information science and machine learning and has never been examined in the field of remote sensing. This study is a novel exploration of ensemble diversity and its link to classification performance, applied to a multi-class canopy cover classification problem using random forests and multisource remote sensing and ancillary GIS data, across seven million hectares of diverse dry-sclerophyll dominated public forests in Victoria Australia. A particular emphasis is placed on analysing the relationship between ensemble diversity and ensemble margin - two key concepts in ensemble learning. The main novelty of our work is on boosting diversity by emphasizing the contribution of lower margin instances used in the learning process. Exploring the influence of tree pruning on diversity is also a new empirical analysis that contributes to a better understanding of ensemble performance. Results reveal insights into the trade-off between ensemble classification accuracy and diversity, and through the ensemble margin, demonstrate how inducing diversity by targeting lower margin training samples is a means of achieving better classifier performance for more difficult or rarer classes and reducing information redundancy in classification problems. Our findings inform strategies for collecting training data and designing and parameterising ensemble classifiers, such as random forests. This is particularly important in large area

  18. Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction.

    Science.gov (United States)

    Faust, Kevin; Xie, Quin; Han, Dominick; Goyle, Kartikay; Volynskaya, Zoya; Djuric, Ugljesa; Diamandis, Phedias

    2018-05-16

    There is growing interest in utilizing artificial intelligence, and particularly deep learning, for computer vision in histopathology. While accumulating studies highlight expert-level performance of convolutional neural networks (CNNs) on focused classification tasks, most studies rely on probability distribution scores with empirically defined cutoff values based on post-hoc analysis. More generalizable tools that allow humans to visualize histology-based deep learning inferences and decision making are scarce. Here, we leverage t-distributed Stochastic Neighbor Embedding (t-SNE) to reduce dimensionality and depict how CNNs organize histomorphologic information. Unique to our workflow, we develop a quantitative and transparent approach to visualizing classification decisions prior to softmax compression. By discretizing the relationships between classes on the t-SNE plot, we show we can super-impose randomly sampled regions of test images and use their distribution to render statistically-driven classifications. Therefore, in addition to providing intuitive outputs for human review, this visual approach can carry out automated and objective multi-class classifications similar to more traditional and less-transparent categorical probability distribution scores. Importantly, this novel classification approach is driven by a priori statistically defined cutoffs. It therefore serves as a generalizable classification and anomaly detection tool less reliant on post-hoc tuning. Routine incorporation of this convenient approach for quantitative visualization and error reduction in histopathology aims to accelerate early adoption of CNNs into generalized real-world applications where unanticipated and previously untrained classes are often encountered.

  19. Knowledge discovery with classification rules in a cardiovascular dataset.

    Science.gov (United States)

    Podgorelec, Vili; Kokol, Peter; Stiglic, Milojka Molan; Hericko, Marjan; Rozman, Ivan

    2005-12-01

    In this paper we study an evolutionary machine learning approach to data mining and knowledge discovery based on the induction of classification rules. A method for automatic rules induction called AREX using evolutionary induction of decision trees and automatic programming is introduced. The proposed algorithm is applied to a cardiovascular dataset consisting of different groups of attributes which should possibly reveal the presence of some specific cardiovascular problems in young patients. A case study is presented that shows the use of AREX for the classification of patients and for discovering possible new medical knowledge from the dataset. The defined knowledge discovery loop comprises a medical expert's assessment of induced rules to drive the evolution of rule sets towards more appropriate solutions. The final result is the discovery of a possible new medical knowledge in the field of pediatric cardiology.

  20. Fast Gaussian kernel learning for classification tasks based on specially structured global optimization.

    Science.gov (United States)

    Zhong, Shangping; Chen, Tianshun; He, Fengying; Niu, Yuzhen

    2014-09-01

    For a practical pattern classification task solved by kernel methods, the computing time is mainly spent on kernel learning (or training). However, the current kernel learning approaches are based on local optimization techniques, and hard to have good time performances, especially for large datasets. Thus the existing algorithms cannot be easily extended to large-scale tasks. In this paper, we present a fast Gaussian kernel learning method by solving a specially structured global optimization (SSGO) problem. We optimize the Gaussian kernel function by using the formulated kernel target alignment criterion, which is a difference of increasing (d.i.) functions. Through using a power-transformation based convexification method, the objective criterion can be represented as a difference of convex (d.c.) functions with a fixed power-transformation parameter. And the objective programming problem can then be converted to a SSGO problem: globally minimizing a concave function over a convex set. The SSGO problem is classical and has good solvability. Thus, to find the global optimal solution efficiently, we can adopt the improved Hoffman's outer approximation method, which need not repeat the searching procedure with different starting points to locate the best local minimum. Also, the proposed method can be proven to converge to the global solution for any classification task. We evaluate the proposed method on twenty benchmark datasets, and compare it with four other Gaussian kernel learning methods. Experimental results show that the proposed method stably achieves both good time-efficiency performance and good classification performance. Copyright © 2014 Elsevier Ltd. All rights reserved.

  1. Motif-Based Text Mining of Microbial Metagenome Redundancy Profiling Data for Disease Classification.

    Science.gov (United States)

    Wang, Yin; Li, Rudong; Zhou, Yuhua; Ling, Zongxin; Guo, Xiaokui; Xie, Lu; Liu, Lei

    2016-01-01

    Text data of 16S rRNA are informative for classifications of microbiota-associated diseases. However, the raw text data need to be systematically processed so that features for classification can be defined/extracted; moreover, the high-dimension feature spaces generated by the text data also pose an additional difficulty. Here we present a Phylogenetic Tree-Based Motif Finding algorithm (PMF) to analyze 16S rRNA text data. By integrating phylogenetic rules and other statistical indexes for classification, we can effectively reduce the dimension of the large feature spaces generated by the text datasets. Using the retrieved motifs in combination with common classification methods, we can discriminate different samples of both pneumonia and dental caries better than other existing methods. We extend the phylogenetic approaches to perform supervised learning on microbiota text data to discriminate the pathological states for pneumonia and dental caries. The results have shown that PMF may enhance the efficiency and reliability in analyzing high-dimension text data.

  2. A Decision-Tree-Oriented Guidance Mechanism for Conducting Nature Science Observation Activities in a Context-Aware Ubiquitous Learning

    Science.gov (United States)

    Hwang, Gwo-Jen; Chu, Hui-Chun; Shih, Ju-Ling; Huang, Shu-Hsien; Tsai, Chin-Chung

    2010-01-01

    A context-aware ubiquitous learning environment is an authentic learning environment with personalized digital supports. While showing the potential of applying such a learning environment, researchers have also indicated the challenges of providing adaptive and dynamic support to individual students. In this paper, a decision-tree-oriented…

  3. A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach.

    Science.gov (United States)

    Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

    2017-06-19

    A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification.

  4. Fast Low-Rank Shared Dictionary Learning for Image Classification.

    Science.gov (United States)

    Tiep Huu Vu; Monga, Vishal

    2017-11-01

    Despite the fact that different objects possess distinct class-specific features, they also usually share common patterns. This observation has been exploited partially in a recently proposed dictionary learning framework by separating the particularity and the commonality (COPAR). Inspired by this, we propose a novel method to explicitly and simultaneously learn a set of common patterns as well as class-specific features for classification with more intuitive constraints. Our dictionary learning framework is hence characterized by both a shared dictionary and particular (class-specific) dictionaries. For the shared dictionary, we enforce a low-rank constraint, i.e., claim that its spanning subspace should have low dimension and the coefficients corresponding to this dictionary should be similar. For the particular dictionaries, we impose on them the well-known constraints stated in the Fisher discrimination dictionary learning (FDDL). Furthermore, we develop new fast and accurate algorithms to solve the subproblems in the learning step, accelerating its convergence. The said algorithms could also be applied to FDDL and its extensions. The efficiencies of these algorithms are theoretically and experimentally verified by comparing their complexities and running time with those of other well-known dictionary learning methods. Experimental results on widely used image data sets establish the advantages of our method over the state-of-the-art dictionary learning methods.

  5. Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

    Directory of Open Access Journals (Sweden)

    Santana Isabel

    2011-08-01

    Full Text Available Abstract Background Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI, but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test. Results Press' Q test showed that all classifiers performed better than chance alone (p Conclusions When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.

  6. Classification of amyloid status using machine learning with histograms of oriented 3D gradients

    Directory of Open Access Journals (Sweden)

    Liam Cattell

    2016-01-01

    Full Text Available Brain amyloid burden may be quantitatively assessed from positron emission tomography imaging using standardised uptake value ratios. Using these ratios as an adjunct to visual image assessment has been shown to improve inter-reader reliability, however, the amyloid positivity threshold is dependent on the tracer and specific image regions used to calculate the uptake ratio. To address this problem, we propose a machine learning approach to amyloid status classification, which is independent of tracer and does not require a specific set of regions of interest. Our method extracts feature vectors from amyloid images, which are based on histograms of oriented three-dimensional gradients. We optimised our method on 133 18F-florbetapir brain volumes, and applied it to a separate test set of 131 volumes. Using the same parameter settings, we then applied our method to 209 11C-PiB images and 128 18F-florbetaben images. We compared our method to classification results achieved using two other methods: standardised uptake value ratios and a machine learning method based on voxel intensities. Our method resulted in the largest mean distances between the subjects and the classification boundary, suggesting that it is less likely to make low-confidence classification decisions. Moreover, our method obtained the highest classification accuracy for all three tracers, and consistently achieved above 96% accuracy.

  7. Naïve and Robust: Class-Conditional Independence in Human Classification Learning

    Science.gov (United States)

    Jarecki, Jana B.; Meder, Björn; Nelson, Jonathan D.

    2018-01-01

    Humans excel in categorization. Yet from a computational standpoint, learning a novel probabilistic classification task involves severe computational challenges. The present paper investigates one way to address these challenges: assuming class-conditional independence of features. This feature independence assumption simplifies the inference…

  8. Phylogenetic classification of bony fishes.

    Science.gov (United States)

    Betancur-R, Ricardo; Wiley, Edward O; Arratia, Gloria; Acero, Arturo; Bailly, Nicolas; Miya, Masaki; Lecointre, Guillaume; Ortí, Guillermo

    2017-07-06

    Fish classifications, as those of most other taxonomic groups, are being transformed drastically as new molecular phylogenies provide support for natural groups that were unanticipated by previous studies. A brief review of the main criteria used by ichthyologists to define their classifications during the last 50 years, however, reveals slow progress towards using an explicit phylogenetic framework. Instead, the trend has been to rely, in varying degrees, on deep-rooted anatomical concepts and authority, often mixing taxa with explicit phylogenetic support with arbitrary groupings. Two leading sources in ichthyology frequently used for fish classifications (JS Nelson's volumes of Fishes of the World and W. Eschmeyer's Catalog of Fishes) fail to adopt a global phylogenetic framework despite much recent progress made towards the resolution of the fish Tree of Life. The first explicit phylogenetic classification of bony fishes was published in 2013, based on a comprehensive molecular phylogeny ( www.deepfin.org ). We here update the first version of that classification by incorporating the most recent phylogenetic results. The updated classification presented here is based on phylogenies inferred using molecular and genomic data for nearly 2000 fishes. A total of 72 orders (and 79 suborders) are recognized in this version, compared with 66 orders in version 1. The phylogeny resolves placement of 410 families, or ~80% of the total of 514 families of bony fishes currently recognized. The ordinal status of 30 percomorph families included in this study, however, remains uncertain (incertae sedis in the series Carangaria, Ovalentaria, or Eupercaria). Comments to support taxonomic decisions and comparisons with conflicting taxonomic groups proposed by others are presented. We also highlight cases were morphological support exist for the groups being classified. This version of the phylogenetic classification of bony fishes is substantially improved, providing resolution

  9. The use of decision trees and naïve Bayes algorithms and trace element patterns for controlling the authenticity of free-range-pastured hens' eggs.

    Science.gov (United States)

    Barbosa, Rommel Melgaço; Nacano, Letícia Ramos; Freitas, Rodolfo; Batista, Bruno Lemos; Barbosa, Fernando

    2014-09-01

    This article aims to evaluate 2 machine learning algorithms, decision trees and naïve Bayes (NB), for egg classification (free-range eggs compared with battery eggs). The database used for the study consisted of 15 chemical elements (As, Ba, Cd, Co, Cs, Cu, Fe, Mg, Mn, Mo, Pb, Se, Sr, V, and Zn) determined in 52 eggs samples (20 free-range and 32 battery eggs) by inductively coupled plasma mass spectrometry. Our results demonstrated that decision trees and NB associated with the mineral contents of eggs provide a high level of accuracy (above 80% and 90%, respectively) for classification between free-range and battery eggs and can be used as an alternative method for adulteration evaluation. © 2014 Institute of Food Technologists®

  10. A Pruning Neural Network Model in Credit Classification Analysis

    Directory of Open Access Journals (Sweden)

    Yajiao Tang

    2018-01-01

    Full Text Available Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency.

  11. Cardiovascular Dysautonomias Diagnosis Using Crisp and Fuzzy Decision Tree: A Comparative Study.

    Science.gov (United States)

    Kadi, Ilham; Idri, Ali

    2016-01-01

    Decision trees (DTs) are one of the most popular techniques for learning classification systems, especially when it comes to learning from discrete examples. In real world, many data occurred in a fuzzy form. Hence a DT must be able to deal with such fuzzy data. In fact, integrating fuzzy logic when dealing with imprecise and uncertain data allows reducing uncertainty and providing the ability to model fine knowledge details. In this paper, a fuzzy decision tree (FDT) algorithm was applied on a dataset extracted from the ANS (Autonomic Nervous System) unit of the Moroccan university hospital Avicenne. This unit is specialized on performing several dynamic tests to diagnose patients with autonomic disorder and suggest them the appropriate treatment. A set of fuzzy classifiers were generated using FID 3.4. The error rates of the generated FDTs were calculated to measure their performances. Moreover, a comparison between the error rates obtained using crisp and FDTs was carried out and has proved that the results of FDTs were better than those obtained using crisp DTs.

  12. Optimizing Multiple Kernel Learning for the Classification of UAV Data

    Directory of Open Access Journals (Sweden)

    Caroline M. Gevaert

    2016-12-01

    Full Text Available Unmanned Aerial Vehicles (UAVs are capable of providing high-quality orthoimagery and 3D information in the form of point clouds at a relatively low cost. Their increasing popularity stresses the necessity of understanding which algorithms are especially suited for processing the data obtained from UAVs. The features that are extracted from the point cloud and imagery have different statistical characteristics and can be considered as heterogeneous, which motivates the use of Multiple Kernel Learning (MKL for classification problems. In this paper, we illustrate the utility of applying MKL for the classification of heterogeneous features obtained from UAV data through a case study of an informal settlement in Kigali, Rwanda. Results indicate that MKL can achieve a classification accuracy of 90.6%, a 5.2% increase over a standard single-kernel Support Vector Machine (SVM. A comparison of seven MKL methods indicates that linearly-weighted kernel combinations based on simple heuristics are competitive with respect to computationally-complex, non-linear kernel combination methods. We further underline the importance of utilizing appropriate feature grouping strategies for MKL, which has not been directly addressed in the literature, and we propose a novel, automated feature grouping method that achieves a high classification accuracy for various MKL methods.

  13. An overview of decision tree applied to power systems

    DEFF Research Database (Denmark)

    Liu, Leo; Rather, Zakir Hussain; Chen, Zhe

    2013-01-01

    The corrosive volume of available data in electric power systems motivate the adoption of data mining techniques in the emerging field of power system data analytics. The mainstream of data mining algorithm applied to power system, Decision Tree (DT), also named as Classification And Regression...... Tree (CART), has gained increasing interests because of its high performance in terms of computational efficiency, uncertainty manageability, and interpretability. This paper presents an overview of a variety of DT applications to power systems for better interfacing of power systems with data...... analytics. The fundamental knowledge of CART algorithm is also introduced which is then followed by examples of both classification tree and regression tree with the help of case study for security assessment of Danish power system....

  14. Machine learning models in breast cancer survival prediction.

    Science.gov (United States)

    Montazeri, Mitra; Montazeri, Mohadeseh; Montazeri, Mahdieh; Beigzadeh, Amin

    2016-01-01

    Breast cancer is one of the most common cancers with a high mortality rate among women. With the early diagnosis of breast cancer survival will increase from 56% to more than 86%. Therefore, an accurate and reliable system is necessary for the early diagnosis of this cancer. The proposed model is the combination of rules and different machine learning techniques. Machine learning models can help physicians to reduce the number of false decisions. They try to exploit patterns and relationships among a large number of cases and predict the outcome of a disease using historical cases stored in datasets. The objective of this study is to propose a rule-based classification method with machine learning techniques for the prediction of different types of Breast cancer survival. We use a dataset with eight attributes that include the records of 900 patients in which 876 patients (97.3%) and 24 (2.7%) patients were females and males respectively. Naive Bayes (NB), Trees Random Forest (TRF), 1-Nearest Neighbor (1NN), AdaBoost (AD), Support Vector Machine (SVM), RBF Network (RBFN), and Multilayer Perceptron (MLP) machine learning techniques with 10-cross fold technique were used with the proposed model for the prediction of breast cancer survival. The performance of machine learning techniques were evaluated with accuracy, precision, sensitivity, specificity, and area under ROC curve. Out of 900 patients, 803 patients and 97 patients were alive and dead, respectively. In this study, Trees Random Forest (TRF) technique showed better results in comparison to other techniques (NB, 1NN, AD, SVM and RBFN, MLP). The accuracy, sensitivity and the area under ROC curve of TRF are 96%, 96%, 93%, respectively. However, 1NN machine learning technique provided poor performance (accuracy 91%, sensitivity 91% and area under ROC curve 78%). This study demonstrates that Trees Random Forest model (TRF) which is a rule-based classification model was the best model with the highest level of

  15. Stock Picking via Nonsymmetrically Pruned Binary Decision Trees

    OpenAIRE

    Anton Andriyashin

    2008-01-01

    Stock picking is the field of financial analysis that is of particular interest for many professional investors and researchers. In this study stock picking is implemented via binary classification trees. Optimal tree size is believed to be the crucial factor in forecasting performance of the trees. While there exists a standard method of tree pruning, which is based on the cost-complexity tradeoff and used in the majority of studies employing binary decision trees, this paper introduces a no...

  16. Evaluation of machine learning algorithms for classification of primary biological aerosol using a new UV-LIF spectrometer

    Science.gov (United States)

    Ruske, Simon; Topping, David O.; Foot, Virginia E.; Kaye, Paul H.; Stanley, Warren R.; Crawford, Ian; Morse, Andrew P.; Gallagher, Martin W.

    2017-03-01

    Characterisation of bioaerosols has important implications within environment and public health sectors. Recent developments in ultraviolet light-induced fluorescence (UV-LIF) detectors such as the Wideband Integrated Bioaerosol Spectrometer (WIBS) and the newly introduced Multiparameter Bioaerosol Spectrometer (MBS) have allowed for the real-time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal spores and pollen.This new generation of instruments has enabled ever larger data sets to be compiled with the aim of studying more complex environments. In real world data sets, particularly those from an urban environment, the population may be dominated by non-biological fluorescent interferents, bringing into question the accuracy of measurements of quantities such as concentrations. It is therefore imperative that we validate the performance of different algorithms which can be used for the task of classification.For unsupervised learning we tested hierarchical agglomerative clustering with various different linkages. For supervised learning, 11 methods were tested, including decision trees, ensemble methods (random forests, gradient boosting and AdaBoost), two implementations for support vector machines (libsvm and liblinear) and Gaussian methods (Gaussian naïve Bayesian, quadratic and linear discriminant analysis, the k-nearest neighbours algorithm and artificial neural networks).The methods were applied to two different data sets produced using the new MBS, which provides multichannel UV-LIF fluorescence signatures for single airborne biological particles. The first data set contained mixed PSLs and the second contained a variety of laboratory-generated aerosol.Clustering in general performs slightly worse than the supervised learning methods, correctly classifying, at best, only 67. 6 and 91. 1 % for the two data sets respectively. For supervised learning the gradient boosting algorithm was

  17. Classification without labels: learning from mixed samples in high energy physics

    Science.gov (United States)

    Metodiev, Eric M.; Nachman, Benjamin; Thaler, Jesse

    2017-10-01

    Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove that the optimal classifier in the CWoLa paradigm is also the optimal classifier in the traditional fully-supervised case where all label information is available. After demonstrating the power of this method in an analytical toy example, we consider a realistic benchmark for collider physics: distinguishing quark- versus gluon-initiated jets using mixed quark/gluon training samples. More generally, CWoLa can be applied to any classification problem where labels or class proportions are unknown or simulations are unreliable, but statistical mixtures of the classes are available.

  18. Comparing the performance of flat and hierarchical Habitat/Land-Cover classification models in a NATURA 2000 site

    Science.gov (United States)

    Gavish, Yoni; O'Connell, Jerome; Marsh, Charles J.; Tarantino, Cristina; Blonda, Palma; Tomaselli, Valeria; Kunin, William E.

    2018-02-01

    The increasing need for high quality Habitat/Land-Cover (H/LC) maps has triggered considerable research into novel machine-learning based classification models. In many cases, H/LC classes follow pre-defined hierarchical classification schemes (e.g., CORINE), in which fine H/LC categories are thematically nested within more general categories. However, none of the existing machine-learning algorithms account for this pre-defined hierarchical structure. Here we introduce a novel Random Forest (RF) based application of hierarchical classification, which fits a separate local classification model in every branching point of the thematic tree, and then integrates all the different local models to a single global prediction. We applied the hierarchal RF approach in a NATURA 2000 site in Italy, using two land-cover (CORINE, FAO-LCCS) and one habitat classification scheme (EUNIS) that differ from one another in the shape of the class hierarchy. For all 3 classification schemes, both the hierarchical model and a flat model alternative provided accurate predictions, with kappa values mostly above 0.9 (despite using only 2.2-3.2% of the study area as training cells). The flat approach slightly outperformed the hierarchical models when the hierarchy was relatively simple, while the hierarchical model worked better under more complex thematic hierarchies. Most misclassifications came from habitat pairs that are thematically distant yet spectrally similar. In 2 out of 3 classification schemes, the additional constraints of the hierarchical model resulted with fewer such serious misclassifications relative to the flat model. The hierarchical model also provided valuable information on variable importance which can shed light into "black-box" based machine learning algorithms like RF. We suggest various ways by which hierarchical classification models can increase the accuracy and interpretability of H/LC classification maps.

  19. Label-free sensor for automatic identification of erythrocytes using digital in-line holographic microscopy and machine learning.

    Science.gov (United States)

    Go, Taesik; Byeon, Hyeokjun; Lee, Sang Joon

    2018-04-30

    Cell types of erythrocytes should be identified because they are closely related to their functionality and viability. Conventional methods for classifying erythrocytes are time consuming and labor intensive. Therefore, an automatic and accurate erythrocyte classification system is indispensable in healthcare and biomedical fields. In this study, we proposed a new label-free sensor for automatic identification of erythrocyte cell types using a digital in-line holographic microscopy (DIHM) combined with machine learning algorithms. A total of 12 features, including information on intensity distributions, morphological descriptors, and optical focusing characteristics, is quantitatively obtained from numerically reconstructed holographic images. All individual features for discocytes, echinocytes, and spherocytes are statistically different. To improve the performance of cell type identification, we adopted several machine learning algorithms, such as decision tree model, support vector machine, linear discriminant classification, and k-nearest neighbor classification. With the aid of these machine learning algorithms, the extracted features are effectively utilized to distinguish erythrocytes. Among the four tested algorithms, the decision tree model exhibits the best identification performance for the training sets (n = 440, 98.18%) and test sets (n = 190, 97.37%). This proposed methodology, which smartly combined DIHM and machine learning, would be helpful for sensing abnormal erythrocytes and computer-aided diagnosis of hematological diseases in clinic. Copyright © 2017 Elsevier B.V. All rights reserved.

  20. Improving Hyperspectral Image Classification Method for Fine Land Use Assessment Application Using Semisupervised Machine Learning

    Directory of Open Access Journals (Sweden)

    Chunyang Wang

    2015-01-01

    Full Text Available Study on land use/cover can reflect changing rules of population, economy, agricultural structure adjustment, policy, and traffic and provide better service for the regional economic development and urban evolution. The study on fine land use/cover assessment using hyperspectral image classification is a focal growing area in many fields. Semisupervised learning method which takes a large number of unlabeled samples and minority labeled samples, improving classification and predicting the accuracy effectively, has been a new research direction. In this paper, we proposed improving fine land use/cover assessment based on semisupervised hyperspectral classification method. The test analysis of study area showed that the advantages of semisupervised classification method could improve the high precision overall classification and objective assessment of land use/cover results.

  1. Supervised learning for the automated transcription of spacer classification from spoligotype films

    Directory of Open Access Journals (Sweden)

    Abernethy Neil

    2009-08-01

    Full Text Available Abstract Background Molecular genotyping of bacteria has revolutionized the study of tuberculosis epidemiology, yet these established laboratory techniques typically require subjective and laborious interpretation by trained professionals. In the context of a Tuberculosis Case Contact study in The Gambia we used a reverse hybridization laboratory assay called spoligotype analysis. To facilitate processing of spoligotype images we have developed tools and algorithms to automate the classification and transcription of these data directly to a database while allowing for manual editing. Results Features extracted from each of the 1849 spots on a spoligo film were classified using two supervised learning algorithms. A graphical user interface allows manual editing of the classification, before export to a database. The application was tested on ten films of differing quality and the results of the best classifier were compared to expert manual classification, giving a median correct classification rate of 98.1% (inter quartile range: 97.1% to 99.2%, with an automated processing time of less than 1 minute per film. Conclusion The software implementation offers considerable time savings over manual processing whilst allowing expert editing of the automated classification. The automatic upload of the classification to a database reduces the chances of transcription errors.

  2. Machine learning in geosciences and remote sensing

    Directory of Open Access Journals (Sweden)

    David J. Lary

    2016-01-01

    Full Text Available Learning incorporates a broad range of complex procedures. Machine learning (ML is a subdivision of artificial intelligence based on the biological learning process. The ML approach deals with the design of algorithms to learn from machine readable data. ML covers main domains such as data mining, difficult-to-program applications, and software applications. It is a collection of a variety of algorithms (e.g. neural networks, support vector machines, self-organizing map, decision trees, random forests, case-based reasoning, genetic programming, etc. that can provide multivariate, nonlinear, nonparametric regression or classification. The modeling capabilities of the ML-based methods have resulted in their extensive applications in science and engineering. Herein, the role of ML as an effective approach for solving problems in geosciences and remote sensing will be highlighted. The unique features of some of the ML techniques will be outlined with a specific attention to genetic programming paradigm. Furthermore, nonparametric regression and classification illustrative examples are presented to demonstrate the efficiency of ML for tackling the geosciences and remote sensing problems.

  3. Study on a pattern classification method of soil quality based on simplified learning sample dataset

    Science.gov (United States)

    Zhang, Jiahua; Liu, S.; Hu, Y.; Tian, Y.

    2011-01-01

    Based on the massive soil information in current soil quality grade evaluation, this paper constructed an intelligent classification approach of soil quality grade depending on classical sampling techniques and disordered multiclassification Logistic regression model. As a case study to determine the learning sample capacity under certain confidence level and estimation accuracy, and use c-means algorithm to automatically extract the simplified learning sample dataset from the cultivated soil quality grade evaluation database for the study area, Long chuan county in Guangdong province, a disordered Logistic classifier model was then built and the calculation analysis steps of soil quality grade intelligent classification were given. The result indicated that the soil quality grade can be effectively learned and predicted by the extracted simplified dataset through this method, which changed the traditional method for soil quality grade evaluation. ?? 2011 IEEE.

  4. Combining extreme learning machines using support vector machines for breast tissue classification.

    Science.gov (United States)

    Daliri, Mohammad Reza

    2015-01-01

    In this paper, we present a new approach for breast tissue classification using the features derived from electrical impedance spectroscopy. This method is composed of a feature extraction method, feature selection phase and a classification step. The feature extraction phase derives the features from the electrical impedance spectra. The extracted features consist of the impedivity at zero frequency (I0), the phase angle at 500 KHz, the high-frequency slope of phase angle, the impedance distance between spectral ends, the area under spectrum, the normalised area, the maximum of the spectrum, the distance between impedivity at I0 and the real part of the maximum frequency point and the length of the spectral curve. The system uses the information theoretic criterion as a strategy for feature selection and the combining extreme learning machines (ELMs) for the classification phase. The results of several ELMs are combined using the support vector machines classifier, and the result of classification is reported as a measure of the performance of the system. The results indicate that the proposed system achieves high accuracy in classification of breast tissues using the electrical impedance spectroscopy.

  5. A method for classification of network traffic based on C5.0 Machine Learning Algorithm

    DEFF Research Database (Denmark)

    Bujlow, Tomasz; Riaz, M. Tahir; Pedersen, Jens Myrup

    2012-01-01

    current network traffic. To overcome the drawbacks of existing methods for traffic classification, usage of C5.0 Machine Learning Algorithm (MLA) was proposed. On the basis of statistical traffic information received from volunteers and C5.0 algorithm we constructed a boosted classifier, which was shown...... and classification, an algorithm for recognizing flow direction and the C5.0 itself. Classified applications include Skype, FTP, torrent, web browser traffic, web radio, interactive gaming and SSH. We performed subsequent tries using different sets of parameters and both training and classification options...

  6. Talking Trees

    Science.gov (United States)

    Tolman, Marvin

    2005-01-01

    Students love outdoor activities and will love them even more when they build confidence in their tree identification and measurement skills. Through these activities, students will learn to identify the major characteristics of trees and discover how the pace--a nonstandard measuring unit--can be used to estimate not only distances but also the…

  7. Computer-aided classification of lung nodules on computed tomography images via deep learning technique

    Directory of Open Access Journals (Sweden)

    Hua KL

    2015-08-01

    Full Text Available Kai-Lung Hua,1 Che-Hao Hsu,1 Shintami Chusnul Hidayati,1 Wen-Huang Cheng,2 Yu-Jen Chen3 1Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, 2Research Center for Information Technology Innovation, Academia Sinica, 3Department of Radiation Oncology, MacKay Memorial Hospital, Taipei, Taiwan Abstract: Lung cancer has a poor prognosis when not diagnosed early and unresectable lesions are present. The management of small lung nodules noted on computed tomography scan is controversial due to uncertain tumor characteristics. A conventional computer-aided diagnosis (CAD scheme requires several image processing and pattern recognition steps to accomplish a quantitative tumor differentiation result. In such an ad hoc image analysis pipeline, every step depends heavily on the performance of the previous step. Accordingly, tuning of classification performance in a conventional CAD scheme is very complicated and arduous. Deep learning techniques, on the other hand, have the intrinsic advantage of an automatic exploitation feature and tuning of performance in a seamless fashion. In this study, we attempted to simplify the image analysis pipeline of conventional CAD with deep learning techniques. Specifically, we introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images. Two baseline methods with feature computing steps were implemented for comparison. The experimental results suggest that deep learning methods could achieve better discriminative results and hold promise in the CAD application domain. Keywords: nodule classification, deep learning, deep belief network, convolutional neural network

  8. Data Processing And Machine Learning Methods For Multi-Modal Operator State Classification Systems

    Science.gov (United States)

    Hearn, Tristan A.

    2015-01-01

    This document is intended as an introduction to a set of common signal processing learning methods that may be used in the software portion of a functional crew state monitoring system. This includes overviews of both the theory of the methods involved, as well as examples of implementation. Practical considerations are discussed for implementing modular, flexible, and scalable processing and classification software for a multi-modal, multi-channel monitoring system. Example source code is also given for all of the discussed processing and classification methods.

  9. Development and Experimental Evaluation of Machine-Learning Techniques for an Intelligent Hairy Scalp Detection System

    Directory of Open Access Journals (Sweden)

    Wei-Chien Wang

    2018-05-01

    Full Text Available Deep learning has become the most popular research subject in the fields of artificial intelligence (AI and machine learning. In October 2013, MIT Technology Review commented that deep learning was a breakthrough technology. Deep learning has made progress in voice and image recognition, image classification, and natural language processing. Prior to deep learning, decision tree, linear discriminant analysis (LDA, support vector machines (SVM, k-nearest neighbors algorithm (K-NN, and ensemble learning were popular in solving classification problems. In this paper, we applied the previously mentioned and deep learning techniques to hairy scalp images. Hairy scalp problems are usually diagnosed by non-professionals in hair salons, and people with such problems may be advised by these non-professionals. Additionally, several common scalp problems are similar; therefore, non-experts may provide incorrect diagnoses. Hence, scalp problems have worsened. In this work, we implemented and compared the deep-learning method, the ImageNet-VGG-f model Bag of Words (BOW, with machine-learning classifiers, and histogram of oriented gradients (HOG/pyramid histogram of oriented gradients (PHOG with machine-learning classifiers. The tools from the classification learner apps were used for hairy scalp image classification. The results indicated that deep learning can achieve an accuracy of 89.77% when the learning rate is 1 × 10−4, and this accuracy is far higher than those achieved by BOW with SVM (80.50% and PHOG with SVM (53.0%.

  10. Decision Tree Technique for Particle Identification

    International Nuclear Information System (INIS)

    Quiller, Ryan

    2003-01-01

    Particle identification based on measurements such as the Cerenkov angle, momentum, and the rate of energy loss per unit distance (-dE/dx) is fundamental to the BaBar detector for particle physics experiments. It is particularly important to separate the charged forms of kaons and pions. Currently, the Neural Net, an algorithm based on mapping input variables to an output variable using hidden variables as intermediaries, is one of the primary tools used for identification. In this study, a decision tree classification technique implemented in the computer program, CART, was investigated and compared to the Neural Net over the range of momenta, 0.25 GeV/c to 5.0 GeV/c. For a given subinterval of momentum, three decision trees were made using different sets of input variables. The sensitivity and specificity were calculated for varying kaon acceptance thresholds. This data was used to plot Receiver Operating Characteristic curves (ROC curves) to compare the performance of the classification methods. Also, input variables used in constructing the decision trees were analyzed. It was found that the Neural Net was a significant contributor to decision trees using dE/dx and the Cerenkov angle as inputs. Furthermore, the Neural Net had poorer performance than the decision tree technique, but tended to improve decision tree performance when used as an input variable. These results suggest that the decision tree technique using Neural Net input may possibly increase accuracy of particle identification in BaBar

  11. Recruiting Conventional Tree Architecture Models into State-of-the-Art LiDAR Mapping for Investigating Tree Growth Habits in Structure.

    Science.gov (United States)

    Lin, Yi; Jiang, Miao; Pellikka, Petri; Heiskanen, Janne

    2018-01-01

    Mensuration of tree growth habits is of considerable importance for understanding forest ecosystem processes and forest biophysical responses to climate changes. However, the complexity of tree crown morphology that is typically formed after many years of growth tends to render it a non-trivial task, even for the state-of-the-art 3D forest mapping technology-light detection and ranging (LiDAR). Fortunately, botanists have deduced the large structural diversity of tree forms into only a limited number of tree architecture models, which can present a-priori knowledge about tree structure, growth, and other attributes for different species. This study attempted to recruit Hallé architecture models (HAMs) into LiDAR mapping to investigate tree growth habits in structure. First, following the HAM-characterized tree structure organization rules, we run the kernel procedure of tree species classification based on the LiDAR-collected point clouds using a support vector machine classifier in the leave-one-out-for-cross-validation mode. Then, the HAM corresponding to each of the classified tree species was identified based on expert knowledge, assisted by the comparison of the LiDAR-derived feature parameters. Next, the tree growth habits in structure for each of the tree species were derived from the determined HAM. In the case of four tree species growing in the boreal environment, the tests indicated that the classification accuracy reached 85.0%, and their growth habits could be derived by qualitative and quantitative means. Overall, the strategy of recruiting conventional HAMs into LiDAR mapping for investigating tree growth habits in structure was validated, thereby paving a new way for efficiently reflecting tree growth habits and projecting forest structure dynamics.

  12. CLASSIFICATION ALGORITHMS FOR BIG DATA ANALYSIS, A MAP REDUCE APPROACH

    Directory of Open Access Journals (Sweden)

    V. A. Ayma

    2015-03-01

    Full Text Available Since many years ago, the scientific community is concerned about how to increase the accuracy of different classification methods, and major achievements have been made so far. Besides this issue, the increasing amount of data that is being generated every day by remote sensors raises more challenges to be overcome. In this work, a tool within the scope of InterIMAGE Cloud Platform (ICP, which is an open-source, distributed framework for automatic image interpretation, is presented. The tool, named ICP: Data Mining Package, is able to perform supervised classification procedures on huge amounts of data, usually referred as big data, on a distributed infrastructure using Hadoop MapReduce. The tool has four classification algorithms implemented, taken from WEKA’s machine learning library, namely: Decision Trees, Naïve Bayes, Random Forest and Support Vector Machines (SVM. The results of an experimental analysis using a SVM classifier on data sets of different sizes for different cluster configurations demonstrates the potential of the tool, as well as aspects that affect its performance.

  13. Comparison of machine learning algorithms for detecting coral reef

    Directory of Open Access Journals (Sweden)

    Eduardo Tusa

    2014-09-01

    Full Text Available (Received: 2014/07/31 - Accepted: 2014/09/23This work focuses on developing a fast coral reef detector, which is used for an autonomous underwater vehicle, AUV. A fast detection secures the AUV stabilization respect to an area of reef as fast as possible, and prevents devastating collisions. We use the algorithm of Purser et al. (2009 because of its precision. This detector has two parts: feature extraction that uses Gabor Wavelet filters, and feature classification that uses machine learning based on Neural Networks. Due to the extensive time of the Neural Networks, we exchange for a classification algorithm based on Decision Trees. We use a database of 621 images of coral reef in Belize (110 images for training and 511 images for testing. We implement the bank of Gabor Wavelets filters using C++ and the OpenCV library. We compare the accuracy and running time of 9 machine learning algorithms, whose result was the selection of the Decision Trees algorithm. Our coral detector performs 70ms of running time in comparison to 22s executed by the algorithm of Purser et al. (2009.

  14. Maximum mutual information regularized classification

    KAUST Repository

    Wang, Jim Jing-Yan

    2014-09-07

    In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned classifier, the uncertainty of the true class label of a data sample should be reduced by knowing its classification response as much as possible. The reduced uncertainty is measured by the mutual information between the classification response and the true class label. To this end, when learning a linear classifier, we propose to maximize the mutual information between classification responses and true class labels of training samples, besides minimizing the classification error and reducing the classifier complexity. An objective function is constructed by modeling mutual information with entropy estimation, and it is optimized by a gradient descend method in an iterative algorithm. Experiments on two real world pattern classification problems show the significant improvements achieved by maximum mutual information regularization.

  15. Maximum mutual information regularized classification

    KAUST Repository

    Wang, Jim Jing-Yan; Wang, Yi; Zhao, Shiguang; Gao, Xin

    2014-01-01

    In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned classifier, the uncertainty of the true class label of a data sample should be reduced by knowing its classification response as much as possible. The reduced uncertainty is measured by the mutual information between the classification response and the true class label. To this end, when learning a linear classifier, we propose to maximize the mutual information between classification responses and true class labels of training samples, besides minimizing the classification error and reducing the classifier complexity. An objective function is constructed by modeling mutual information with entropy estimation, and it is optimized by a gradient descend method in an iterative algorithm. Experiments on two real world pattern classification problems show the significant improvements achieved by maximum mutual information regularization.

  16. A comparative study of deep learning models for medical image classification

    Science.gov (United States)

    Dutta, Suvajit; Manideep, B. C. S.; Rai, Shalva; Vijayarajan, V.

    2017-11-01

    Deep Learning(DL) techniques are conquering over the prevailing traditional approaches of neural network, when it comes to the huge amount of dataset, applications requiring complex functions demanding increase accuracy with lower time complexities. Neurosciences has already exploited DL techniques, thus portrayed itself as an inspirational source for researchers exploring the domain of Machine learning. DL enthusiasts cover the areas of vision, speech recognition, motion planning and NLP as well, moving back and forth among fields. This concerns with building models that can successfully solve variety of tasks requiring intelligence and distributed representation. The accessibility to faster CPUs, introduction of GPUs-performing complex vector and matrix computations, supported agile connectivity to network. Enhanced software infrastructures for distributed computing worked in strengthening the thought that made researchers suffice DL methodologies. The paper emphases on the following DL procedures to traditional approaches which are performed manually for classifying medical images. The medical images are used for the study Diabetic Retinopathy(DR) and computed tomography (CT) emphysema data. Both DR and CT data diagnosis is difficult task for normal image classification methods. The initial work was carried out with basic image processing along with K-means clustering for identification of image severity levels. After determining image severity levels ANN has been applied on the data to get the basic classification result, then it is compared with the result of DNNs (Deep Neural Networks), which performed efficiently because of its multiple hidden layer features basically which increases accuracy factors, but the problem of vanishing gradient in DNNs made to consider Convolution Neural Networks (CNNs) as well for better results. The CNNs are found to be providing better outcomes when compared to other learning models aimed at classification of images. CNNs are

  17. The gravity apple tree

    International Nuclear Information System (INIS)

    Aldama, Mariana Espinosa

    2015-01-01

    The gravity apple tree is a genealogical tree of the gravitation theories developed during the past century. The graphic representation is full of information such as guides in heuristic principles, names of main proponents, dates and references for original articles (See under Supplementary Data for the graphic representation). This visual presentation and its particular classification allows a quick synthetic view for a plurality of theories, many of them well validated in the Solar System domain. Its diachronic structure organizes information in a shape of a tree following similarities through a formal concept analysis. It can be used for educational purposes or as a tool for philosophical discussion. (paper)

  18. Meta-Learning Approach for Automatic Parameter Tuning: A Case Study with Educational Datasets

    Science.gov (United States)

    Molina, M. M.; Luna, J. M.; Romero, C.; Ventura, S.

    2012-01-01

    This paper proposes to the use of a meta-learning approach for automatic parameter tuning of a well-known decision tree algorithm by using past information about algorithm executions. Fourteen educational datasets were analysed using various combinations of parameter values to examine the effects of the parameter values on accuracy classification.…

  19. Application of machine learning on brain cancer multiclass classification

    Science.gov (United States)

    Panca, V.; Rustam, Z.

    2017-07-01

    Classification of brain cancer is a problem of multiclass classification. One approach to solve this problem is by first transforming it into several binary problems. The microarray gene expression dataset has the two main characteristics of medical data: extremely many features (genes) and only a few number of samples. The application of machine learning on microarray gene expression dataset mainly consists of two steps: feature selection and classification. In this paper, the features are selected using a method based on support vector machine recursive feature elimination (SVM-RFE) principle which is improved to solve multiclass classification, called multiple multiclass SVM-RFE. Instead of using only the selected features on a single classifier, this method combines the result of multiple classifiers. The features are divided into subsets and SVM-RFE is used on each subset. Then, the selected features on each subset are put on separate classifiers. This method enhances the feature selection ability of each single SVM-RFE. Twin support vector machine (TWSVM) is used as the method of the classifier to reduce computational complexity. While ordinary SVM finds single optimum hyperplane, the main objective Twin SVM is to find two non-parallel optimum hyperplanes. The experiment on the brain cancer microarray gene expression dataset shows this method could classify 71,4% of the overall test data correctly, using 100 and 1000 genes selected from multiple multiclass SVM-RFE feature selection method. Furthermore, the per class results show that this method could classify data of normal and MD class with 100% accuracy.

  20. Lesion classification using clinical and visual data fusion by multiple kernel learning

    Science.gov (United States)

    Kisilev, Pavel; Hashoul, Sharbell; Walach, Eugene; Tzadok, Asaf

    2014-03-01

    To overcome operator dependency and to increase diagnosis accuracy in breast ultrasound (US), a lot of effort has been devoted to developing computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Unfortunately, the efficacy of such CAD systems is limited since they rely on correct automatic lesions detection and localization, and on robustness of features computed based on the detected areas. In this paper we propose a new approach to boost the performance of a Machine Learning based CAD system, by combining visual and clinical data from patient files. We compute a set of visual features from breast ultrasound images, and construct the textual descriptor of patients by extracting relevant keywords from patients' clinical data files. We then use the Multiple Kernel Learning (MKL) framework to train SVM based classifier to discriminate between benign and malignant cases. We investigate different types of data fusion methods, namely, early, late, and intermediate (MKL-based) fusion. Our database consists of 408 patient cases, each containing US images, textual description of complaints and symptoms filled by physicians, and confirmed diagnoses. We show experimentally that the proposed MKL-based approach is superior to other classification methods. Even though the clinical data is very sparse and noisy, its MKL-based fusion with visual features yields significant improvement of the classification accuracy, as compared to the image features only based classifier.

  1. A renewed perspective on agroforestry concepts and classification.

    Science.gov (United States)

    Torquebiau, E F

    2000-11-01

    Agroforestry, the association of trees with farming practices, is progressively becoming a recognized land-use discipline. However, it is still perceived by some scientists, technicians and farmers as a sort of environmental fashion which does not deserve credit. The peculiar history of agroforestry and the complex relationships between agriculture and forestry explain some misunderstandings about the concepts and classification of agroforestry and reveal that, contrarily to common perception, agroforestry is closer to agriculture than to forestry. Based on field experience from several countries, a structural classification of agroforestry into six simple categories is proposed: crops under tree cover, agroforests, agroforestry in a linear arrangement, animal agroforestry, sequential agroforestry and minor agroforestry techniques. It is argued that this pragmatic classification encompasses all major agroforestry associations and allows simultaneous agroforestry to be clearly differentiated from sequential agroforestry, two categories showing contrasting ecological tree-crop interactions. It can also contribute to a betterment of the image of agroforestry and lead to a simplification of its definition.

  2. An automated approach to the design of decision tree classifiers

    Science.gov (United States)

    Argentiero, P.; Chin, R.; Beaudet, P.

    1982-01-01

    An automated technique is presented for designing effective decision tree classifiers predicated only on a priori class statistics. The procedure relies on linear feature extractions and Bayes table look-up decision rules. Associated error matrices are computed and utilized to provide an optimal design of the decision tree at each so-called 'node'. A by-product of this procedure is a simple algorithm for computing the global probability of correct classification assuming the statistical independence of the decision rules. Attention is given to a more precise definition of decision tree classification, the mathematical details on the technique for automated decision tree design, and an example of a simple application of the procedure using class statistics acquired from an actual Landsat scene.

  3. Exploratory analysis of methods for automated classification of laboratory test orders into syndromic groups in veterinary medicine.

    Directory of Open Access Journals (Sweden)

    Fernanda C Dórea

    Full Text Available BACKGROUND: Recent focus on earlier detection of pathogen introduction in human and animal populations has led to the development of surveillance systems based on automated monitoring of health data. Real- or near real-time monitoring of pre-diagnostic data requires automated classification of records into syndromes--syndromic surveillance--using algorithms that incorporate medical knowledge in a reliable and efficient way, while remaining comprehensible to end users. METHODS: This paper describes the application of two of machine learning (Naïve Bayes and Decision Trees and rule-based methods to extract syndromic information from laboratory test requests submitted to a veterinary diagnostic laboratory. RESULTS: High performance (F1-macro = 0.9995 was achieved through the use of a rule-based syndrome classifier, based on rule induction followed by manual modification during the construction phase, which also resulted in clear interpretability of the resulting classification process. An unmodified rule induction algorithm achieved an F(1-micro score of 0.979 though this fell to 0.677 when performance for individual classes was averaged in an unweighted manner (F(1-macro, due to the fact that the algorithm failed to learn 3 of the 16 classes from the training set. Decision Trees showed equal interpretability to the rule-based approaches, but achieved an F(1-micro score of 0.923 (falling to 0.311 when classes are given equal weight. A Naïve Bayes classifier learned all classes and achieved high performance (F(1-micro= 0.994 and F(1-macro = .955, however the classification process is not transparent to the domain experts. CONCLUSION: The use of a manually customised rule set allowed for the development of a system for classification of laboratory tests into syndromic groups with very high performance, and high interpretability by the domain experts. Further research is required to develop internal validation rules in order to establish

  4. Classification and Analysis of Computer Network Traffic

    DEFF Research Database (Denmark)

    Bujlow, Tomasz

    2014-01-01

    various classification modes (decision trees, rulesets, boosting, softening thresholds) regarding the classification accuracy and the time required to create the classifier. We showed how to use our VBS tool to obtain per-flow, per-application, and per-content statistics of traffic in computer networks...

  5. Automated Classification of Radiology Reports for Acute Lung Injury: Comparison of Keyword and Machine Learning Based Natural Language Processing Approaches.

    Science.gov (United States)

    Solti, Imre; Cooke, Colin R; Xia, Fei; Wurfel, Mark M

    2009-11-01

    This paper compares the performance of keyword and machine learning-based chest x-ray report classification for Acute Lung Injury (ALI). ALI mortality is approximately 30 percent. High mortality is, in part, a consequence of delayed manual chest x-ray classification. An automated system could reduce the time to recognize ALI and lead to reductions in mortality. For our study, 96 and 857 chest x-ray reports in two corpora were labeled by domain experts for ALI. We developed a keyword and a Maximum Entropy-based classification system. Word unigram and character n-grams provided the features for the machine learning system. The Maximum Entropy algorithm with character 6-gram achieved the highest performance (Recall=0.91, Precision=0.90 and F-measure=0.91) on the 857-report corpus. This study has shown that for the classification of ALI chest x-ray reports, the machine learning approach is superior to the keyword based system and achieves comparable results to highest performing physician annotators.

  6. Statistical Discriminability Estimation for Pattern Classification Based on Neural Incremental Attribute Learning

    DEFF Research Database (Denmark)

    Wang, Ting; Guan, Sheng-Uei; Puthusserypady, Sadasivan

    2014-01-01

    Feature ordering is a significant data preprocessing method in Incremental Attribute Learning (IAL), a novel machine learning approach which gradually trains features according to a given order. Previous research has shown that, similar to feature selection, feature ordering is also important based...... estimation. Moreover, a criterion that summarizes all the produced values of AD is employed with a GA (Genetic Algorithm)-based approach to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. Compared with the feature ordering obtained by other approaches...

  7. Motif-Based Text Mining of Microbial Metagenome Redundancy Profiling Data for Disease Classification

    Directory of Open Access Journals (Sweden)

    Yin Wang

    2016-01-01

    Full Text Available Background. Text data of 16S rRNA are informative for classifications of microbiota-associated diseases. However, the raw text data need to be systematically processed so that features for classification can be defined/extracted; moreover, the high-dimension feature spaces generated by the text data also pose an additional difficulty. Results. Here we present a Phylogenetic Tree-Based Motif Finding algorithm (PMF to analyze 16S rRNA text data. By integrating phylogenetic rules and other statistical indexes for classification, we can effectively reduce the dimension of the large feature spaces generated by the text datasets. Using the retrieved motifs in combination with common classification methods, we can discriminate different samples of both pneumonia and dental caries better than other existing methods. Conclusions. We extend the phylogenetic approaches to perform supervised learning on microbiota text data to discriminate the pathological states for pneumonia and dental caries. The results have shown that PMF may enhance the efficiency and reliability in analyzing high-dimension text data.

  8. An Empirical Overview of the No Free Lunch Theorem and Its Effect on Real-World Machine Learning Classification.

    Science.gov (United States)

    Gómez, David; Rojas, Alfonso

    2016-01-01

    A sizable amount of research has been done to improve the mechanisms for knowledge extraction such as machine learning classification or regression. Quite unintuitively, the no free lunch (NFL) theorem states that all optimization problem strategies perform equally well when averaged over all possible problems. This fact seems to clash with the effort put forth toward better algorithms. This letter explores empirically the effect of the NFL theorem on some popular machine learning classification techniques over real-world data sets.

  9. Forest tree species discrimination in western Himalaya using EO-1 Hyperion

    Science.gov (United States)

    George, Rajee; Padalia, Hitendra; Kushwaha, S. P. S.

    2014-05-01

    The information acquired in the narrow bands of hyperspectral remote sensing data has potential to capture plant species spectral variability, thereby improving forest tree species mapping. This study assessed the utility of spaceborne EO-1 Hyperion data in discrimination and classification of broadleaved evergreen and conifer forest tree species in western Himalaya. The pre-processing of 242 bands of Hyperion data resulted into 160 noise-free and vertical stripe corrected reflectance bands. Of these, 29 bands were selected through step-wise exclusion of bands (Wilk's Lambda). Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) algorithms were applied to the selected bands to assess their effectiveness in classification. SVM was also applied to broadband data (Landsat TM) to compare the variation in classification accuracy. All commonly occurring six gregarious tree species, viz., white oak, brown oak, chir pine, blue pine, cedar and fir in western Himalaya could be effectively discriminated. SVM produced a better species classification (overall accuracy 82.27%, kappa statistic 0.79) than SAM (overall accuracy 74.68%, kappa statistic 0.70). It was noticed that classification accuracy achieved with Hyperion bands was significantly higher than Landsat TM bands (overall accuracy 69.62%, kappa statistic 0.65). Study demonstrated the potential utility of narrow spectral bands of Hyperion data in discriminating tree species in a hilly terrain.

  10. Classification tree analysis of second neoplasms in survivors of childhood cancer

    International Nuclear Information System (INIS)

    Jazbec, Janez; Todorovski, Ljupčo; Jereb, Berta

    2007-01-01

    Reports on childhood cancer survivors estimated cumulative probability of developing secondary neoplasms vary from 3,3% to 25% at 25 years from diagnosis, and the risk of developing another cancer to several times greater than in the general population. In our retrospective study, we have used the classification tree multivariate method on a group of 849 first cancer survivors, to identify childhood cancer patients with the greatest risk for development of secondary neoplasms. In observed group of patients, 34 develop secondary neoplasm after treatment of primary cancer. Analysis of parameters present at the treatment of first cancer, exposed two groups of patients at the special risk for secondary neoplasm. First are female patients treated for Hodgkin's disease at the age between 10 and 15 years, whose treatment included radiotherapy. Second group at special risk were male patients with acute lymphoblastic leukemia who were treated at the age between 4,6 and 6,6 years of age. The risk groups identified in our study are similar to the results of studies that used more conventional approaches. Usefulness of our approach in study of occurrence of second neoplasms should be confirmed in larger sample study, but user friendly presentation of results makes it attractive for further studies

  11. Poster abstract: A machine learning approach for vehicle classification using passive infrared and ultrasonic sensors

    KAUST Repository

    Warriach, Ehsan Ullah

    2013-01-01

    This article describes the implementation of four different machine learning techniques for vehicle classification in a dual ultrasonic/passive infrared traffic flow sensors. Using k-NN, Naive Bayes, SVM and KNN-SVM algorithms, we show that KNN-SVM significantly outperforms other algorithms in terms of classification accuracy. We also show that some of these algorithms could run in real time on the prototype system. Copyright © 2013 ACM.

  12. The importance of chemosensory clues in Aguaruna tree classification and identification.

    Science.gov (United States)

    Jernigan, Kevin A

    2008-05-03

    The ethnobotanical literature still contains few detailed descriptions of the sensory criteria people use for judging membership in taxonomic categories. Olfactory criteria in particular have been explored very little. This paper will describe the importance of odor for woody plant taxonomy and identification among the Aguaruna Jívaro of the northern Peruvian Amazon, focusing on the Aguaruna category númi (trees excluding palms). Aguaruna informants almost always place trees that they consider to have a similar odor together as kumpají - 'companions,' a metaphor they use to describe trees that they consider to be related. The research took place in several Aguaruna communities in the upper Marañón region of the Peruvian Amazon. Structured interview data focus on informant criteria for membership in various folk taxa of trees. Informants were also asked to explain what members of each group of related companions had in common. This paper focuses on odor and taste criteria that came to light during these structured interviews. Botanical voucher specimens were collected, wherever possible. Of the 182 tree folk genera recorded in this study, 51 (28%) were widely considered to possess a distinctive odor. Thirty nine of those (76%) were said to have odors similar to some other tree, while the other 24% had unique odors. Aguaruna informants very rarely described tree odors in non-botanical terms. Taste was used mostly to describe trees with edible fruits. Trees judged to be related were nearly always in the same botanical family. The results of this study illustrate that odor of bark, sap, flowers, fruit and leaves are important clues that help the Aguaruna to judge the relatedness of trees found in their local environment. In contrast, taste appears to play a more limited role. The results suggest a more general ethnobotanical hypothesis that could be tested in other cultural settings: people tend to consider plants with similar odors to be related, but say that

  13. The importance of chemosensory clues in Aguaruna tree classification and identification

    Directory of Open Access Journals (Sweden)

    Jernigan Kevin A

    2008-05-01

    Full Text Available Abstract Background The ethnobotanical literature still contains few detailed descriptions of the sensory criteria people use for judging membership in taxonomic categories. Olfactory criteria in particular have been explored very little. This paper will describe the importance of odor for woody plant taxonomy and identification among the Aguaruna Jívaro of the northern Peruvian Amazon, focusing on the Aguaruna category númi (trees excluding palms. Aguaruna informants almost always place trees that they consider to have a similar odor together as kumpají – 'companions,' a metaphor they use to describe trees that they consider to be related. Methods The research took place in several Aguaruna communities in the upper Marañón region of the Peruvian Amazon. Structured interview data focus on informant criteria for membership in various folk taxa of trees. Informants were also asked to explain what members of each group of related companions had in common. This paper focuses on odor and taste criteria that came to light during these structured interviews. Botanical voucher specimens were collected, wherever possible. Results Of the 182 tree folk genera recorded in this study, 51 (28% were widely considered to possess a distinctive odor. Thirty nine of those (76% were said to have odors similar to some other tree, while the other 24% had unique odors. Aguaruna informants very rarely described tree odors in non-botanical terms. Taste was used mostly to describe trees with edible fruits. Trees judged to be related were nearly always in the same botanical family. Conclusion The results of this study illustrate that odor of bark, sap, flowers, fruit and leaves are important clues that help the Aguaruna to judge the relatedness of trees found in their local environment. In contrast, taste appears to play a more limited role. The results suggest a more general ethnobotanical hypothesis that could be tested in other cultural settings: people tend to

  14. A Semi-Automated Machine Learning Algorithm for Tree Cover Delineation from 1-m Naip Imagery Using a High Performance Computing Architecture

    Science.gov (United States)

    Basu, S.; Ganguly, S.; Nemani, R. R.; Mukhopadhyay, S.; Milesi, C.; Votava, P.; Michaelis, A.; Zhang, G.; Cook, B. D.; Saatchi, S. S.; Boyda, E.

    2014-12-01

    Accurate tree cover delineation is a useful instrument in the derivation of Above Ground Biomass (AGB) density estimates from Very High Resolution (VHR) satellite imagery data. Numerous algorithms have been designed to perform tree cover delineation in high to coarse resolution satellite imagery, but most of them do not scale to terabytes of data, typical in these VHR datasets. In this paper, we present an automated probabilistic framework for the segmentation and classification of 1-m VHR data as obtained from the National Agriculture Imagery Program (NAIP) for deriving tree cover estimates for the whole of Continental United States, using a High Performance Computing Architecture. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on Conditional Random Field (CRF), which helps in capturing the higher order contextual dependencies between neighboring pixels. Once the final probability maps are generated, the framework is updated and re-trained by incorporating expert knowledge through the relabeling of misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates. The tree cover maps were generated for the state of California, which covers a total of 11,095 NAIP tiles and spans a total geographical area of 163,696 sq. miles. Our framework produced correct detection rates of around 85% for fragmented forests and 70% for urban tree cover areas, with false positive rates lower than 3% for both regions. Comparative studies with the National Land Cover Data (NLCD) algorithm and the LiDAR high-resolution canopy height model shows the effectiveness of our algorithm in generating accurate high-resolution tree cover maps.

  15. Sentiment classification technology based on Markov logic networks

    Science.gov (United States)

    He, Hui; Li, Zhigang; Yao, Chongchong; Zhang, Weizhe

    2016-07-01

    With diverse online media emerging, there is a growing concern of sentiment classification problem. At present, text sentiment classification mainly utilizes supervised machine learning methods, which feature certain domain dependency. On the basis of Markov logic networks (MLNs), this study proposed a cross-domain multi-task text sentiment classification method rooted in transfer learning. Through many-to-one knowledge transfer, labeled text sentiment classification, knowledge was successfully transferred into other domains, and the precision of the sentiment classification analysis in the text tendency domain was improved. The experimental results revealed the following: (1) the model based on a MLN demonstrated higher precision than the single individual learning plan model. (2) Multi-task transfer learning based on Markov logical networks could acquire more knowledge than self-domain learning. The cross-domain text sentiment classification model could significantly improve the precision and efficiency of text sentiment classification.

  16. Ensemble Deep Learning for Biomedical Time Series Classification

    Directory of Open Access Journals (Sweden)

    Lin-peng Jin

    2016-01-01

    Full Text Available Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost.

  17. Classification of large-sized hyperspectral imagery using fast machine learning algorithms

    Science.gov (United States)

    Xia, Junshi; Yokoya, Naoto; Iwasaki, Akira

    2017-07-01

    We present a framework of fast machine learning algorithms in the context of large-sized hyperspectral images classification from the theoretical to a practical viewpoint. In particular, we assess the performance of random forest (RF), rotation forest (RoF), and extreme learning machine (ELM) and the ensembles of RF and ELM. These classifiers are applied to two large-sized hyperspectral images and compared to the support vector machines. To give the quantitative analysis, we pay attention to comparing these methods when working with high input dimensions and a limited/sufficient training set. Moreover, other important issues such as the computational cost and robustness against the noise are also discussed.

  18. Tree detection in urban regions from aerial imagery and DSM based on local maxima points

    Science.gov (United States)

    Korkmaz, Özgür; Yardımcı ćetin, Yasemin; Yilmaz, Erdal

    2017-05-01

    In this study, we propose an automatic approach for tree detection and classification in registered 3-band aerial images and associated digital surface models (DSM). The tree detection results can be used in 3D city modelling and urban planning. This problem is magnified when trees are in close proximity to each other or other objects such as rooftops in the scenes. This study presents a method for locating individual trees and estimation of crown size based on local maxima from DSM accompanied by color and texture information. For this purpose, segment level classifier trained for 10 classes and classification results are improved by analyzing the class probabilities of neighbour segments. Later, the tree classes under a certain height were eliminated using the Digital Terrain Model (DTM). For the tree classes, local maxima points are obtained and the tree radius estimate is made from the vertical and horizontal height profiles passing through these points. The final tree list containing the centers and radius of the trees is obtained by selecting from the list of tree candidates according to the overlapping and selection parameters. Although the limited number of train sets are used in this study, tree classification and localization results are competitive.

  19. Recruiting Conventional Tree Architecture Models into State-of-the-Art LiDAR Mapping for Investigating Tree Growth Habits in Structure

    Directory of Open Access Journals (Sweden)

    Yi Lin

    2018-02-01

    Full Text Available Mensuration of tree growth habits is of considerable importance for understanding forest ecosystem processes and forest biophysical responses to climate changes. However, the complexity of tree crown morphology that is typically formed after many years of growth tends to render it a non-trivial task, even for the state-of-the-art 3D forest mapping technology—light detection and ranging (LiDAR. Fortunately, botanists have deduced the large structural diversity of tree forms into only a limited number of tree architecture models, which can present a-priori knowledge about tree structure, growth, and other attributes for different species. This study attempted to recruit Hallé architecture models (HAMs into LiDAR mapping to investigate tree growth habits in structure. First, following the HAM-characterized tree structure organization rules, we run the kernel procedure of tree species classification based on the LiDAR-collected point clouds using a support vector machine classifier in the leave-one-out-for-cross-validation mode. Then, the HAM corresponding to each of the classified tree species was identified based on expert knowledge, assisted by the comparison of the LiDAR-derived feature parameters. Next, the tree growth habits in structure for each of the tree species were derived from the determined HAM. In the case of four tree species growing in the boreal environment, the tests indicated that the classification accuracy reached 85.0%, and their growth habits could be derived by qualitative and quantitative means. Overall, the strategy of recruiting conventional HAMs into LiDAR mapping for investigating tree growth habits in structure was validated, thereby paving a new way for efficiently reflecting tree growth habits and projecting forest structure dynamics.

  20. Joint learning and weighting of visual vocabulary for bag-of-feature based tissue classification

    KAUST Repository

    Wang, Jim Jing-Yan; Bensmail, Halima; Gao, Xin

    2013-01-01

    their power in this field. Two important issues of bag-of-feature strategy for tissue classification are investigated in this paper: the visual vocabulary learning and weighting, which are always considered independently in traditional methods by neglecting

  1. Evaluation of Semi-supervised Learning for Classification of Protein Crystallization Imagery.

    Science.gov (United States)

    Sigdel, Madhav; Dinç, İmren; Dinç, Semih; Sigdel, Madhu S; Pusey, Marc L; Aygün, Ramazan S

    2014-03-01

    In this paper, we investigate the performance of two wrapper methods for semi-supervised learning algorithms for classification of protein crystallization images with limited labeled images. Firstly, we evaluate the performance of semi-supervised approach using self-training with naïve Bayesian (NB) and sequential minimum optimization (SMO) as the base classifiers. The confidence values returned by these classifiers are used to select high confident predictions to be used for self-training. Secondly, we analyze the performance of Yet Another Two Stage Idea (YATSI) semi-supervised learning using NB, SMO, multilayer perceptron (MLP), J48 and random forest (RF) classifiers. These results are compared with the basic supervised learning using the same training sets. We perform our experiments on a dataset consisting of 2250 protein crystallization images for different proportions of training and test data. Our results indicate that NB and SMO using both self-training and YATSI semi-supervised approaches improve accuracies with respect to supervised learning. On the other hand, MLP, J48 and RF perform better using basic supervised learning. Overall, random forest classifier yields the best accuracy with supervised learning for our dataset.

  2. Comparisons and Selections of Features and Classifiers for Short Text Classification

    Science.gov (United States)

    Wang, Ye; Zhou, Zhi; Jin, Shan; Liu, Debin; Lu, Mi

    2017-10-01

    Short text is considerably different from traditional long text documents due to its shortness and conciseness, which somehow hinders the applications of conventional machine learning and data mining algorithms in short text classification. According to traditional artificial intelligence methods, we divide short text classification into three steps, namely preprocessing, feature selection and classifier comparison. In this paper, we have illustrated step-by-step how we approach our goals. Specifically, in feature selection, we compared the performance and robustness of the four methods of one-hot encoding, tf-idf weighting, word2vec and paragraph2vec, and in the classification part, we deliberately chose and compared Naive Bayes, Logistic Regression, Support Vector Machine, K-nearest Neighbor and Decision Tree as our classifiers. Then, we compared and analysed the classifiers horizontally with each other and vertically with feature selections. Regarding the datasets, we crawled more than 400,000 short text files from Shanghai and Shenzhen Stock Exchanges and manually labeled them into two classes, the big and the small. There are eight labels in the big class, and 59 labels in the small class.

  3. Bagging Approach for Increasing Classification Accuracy of CART on Family Participation Prediction in Implementation of Elderly Family Development Program

    Directory of Open Access Journals (Sweden)

    Wisoedhanie Widi Anugrahanti

    2017-06-01

    Full Text Available Classification and Regression Tree (CART was a method of Machine Learning where data exploration was done by decision tree technique. CART was a classification technique with binary recursive reconciliation algorithms where the sorting was performed on a group of data collected in a space called a node / node into two child nodes (Lewis, 2000. The aim of this study was to predict family participation in Elderly Family Development program based on family behavior in providing physical, mental, social care for the elderly. Family involvement accuracy using Bagging CART method was calculated based on 1-APER value, sensitivity, specificity, and G-Means. Based on CART method, classification accuracy was obtained 97,41% with Apparent Error Rate value 2,59%. The most important determinant of family behavior as a sorter was society participation (100,00000, medical examination (98,95988, providing nutritious food (68.60476, establishing communication (67,19877 and worship (57,36587. To improved the stability and accuracy of CART prediction, used CART Bootstrap Aggregating (Bagging with 100% accuracy result. Bagging CART classifies a total of 590 families (84.77% were appropriately classified into implement elderly Family Development program class.

  4. Learning a constrained conditional random field for enhanced segmentation of fallen trees in ALS point clouds

    Science.gov (United States)

    Polewski, Przemyslaw; Yao, Wei; Heurich, Marco; Krzystek, Peter; Stilla, Uwe

    2018-06-01

    In this study, we present a method for improving the quality of automatic single fallen tree stem segmentation in ALS data by applying a specialized constrained conditional random field (CRF). The entire processing pipeline is composed of two steps. First, short stem segments of equal length are detected and a subset of them is selected for further processing, while in the second step the chosen segments are merged to form entire trees. The first step is accomplished using the specialized CRF defined on the space of segment labelings, capable of finding segment candidates which are easier to merge subsequently. To achieve this, the CRF considers not only the features of every candidate individually, but incorporates pairwise spatial interactions between adjacent segments into the model. In particular, pairwise interactions include a collinearity/angular deviation probability which is learned from training data as well as the ratio of spatial overlap, whereas unary potentials encode a learned probabilistic model of the laser point distribution around each segment. Each of these components enters the CRF energy with its own balance factor. To process previously unseen data, we first calculate the subset of segments for merging on a grid of balance factors by minimizing the CRF energy. Then, we perform the merging and rank the balance configurations according to the quality of their resulting merged trees, obtained from a learned tree appearance model. The final result is derived from the top-ranked configuration. We tested our approach on 5 plots from the Bavarian Forest National Park using reference data acquired in a field inventory. Compared to our previous segment selection method without pairwise interactions, an increase in detection correctness and completeness of up to 7 and 9 percentage points, respectively, was observed.

  5. Identifying Domain-General and Domain-Specific Predictors of Low Mathematics Performance: A Classification and Regression Tree Analysis

    Directory of Open Access Journals (Sweden)

    David J. Purpura

    2017-12-01

    Full Text Available Many children struggle to successfully acquire early mathematics skills. Theoretical and empirical evidence has pointed to deficits in domain-specific skills (e.g., non-symbolic mathematics skills or domain-general skills (e.g., executive functioning and language as underlying low mathematical performance. In the current study, we assessed a sample of 113 three- to five-year old preschool children on a battery of domain-specific and domain-general factors in the fall and spring of their preschool year to identify Time 1 (fall factors associated with low performance in mathematics knowledge at Time 2 (spring. We used the exploratory approach of classification and regression tree analyses, a strategy that uses step-wise partitioning to create subgroups from a larger sample using multiple predictors, to identify the factors that were the strongest classifiers of low performance for younger and older preschool children. Results indicated that the most consistent classifier of low mathematics performance at Time 2 was children’s Time 1 mathematical language skills. Further, other distinct classifiers of low performance emerged for younger and older children. These findings suggest that risk classification for low mathematics performance may differ depending on children’s age.

  6. Mapping Urban Tree Canopy Cover Using Fused Airborne LIDAR and Satellite Imagery Data

    Science.gov (United States)

    Parmehr, Ebadat G.; Amati, Marco; Fraser, Clive S.

    2016-06-01

    Urban green spaces, particularly urban trees, play a key role in enhancing the liveability of cities. The availability of accurate and up-to-date maps of tree canopy cover is important for sustainable development of urban green spaces. LiDAR point clouds are widely used for the mapping of buildings and trees, and several LiDAR point cloud classification techniques have been proposed for automatic mapping. However, the effectiveness of point cloud classification techniques for automated tree extraction from LiDAR data can be impacted to the point of failure by the complexity of tree canopy shapes in urban areas. Multispectral imagery, which provides complementary information to LiDAR data, can improve point cloud classification quality. This paper proposes a reliable method for the extraction of tree canopy cover from fused LiDAR point cloud and multispectral satellite imagery data. The proposed method initially associates each LiDAR point with spectral information from the co-registered satellite imagery data. It calculates the normalised difference vegetation index (NDVI) value for each LiDAR point and corrects tree points which have been misclassified as buildings. Then, region growing of tree points, taking the NDVI value into account, is applied. Finally, the LiDAR points classified as tree points are utilised to generate a canopy cover map. The performance of the proposed tree canopy cover mapping method is experimentally evaluated on a data set of airborne LiDAR and WorldView 2 imagery covering a suburb in Melbourne, Australia.

  7. The Tree of Industrial Life

    DEFF Research Database (Denmark)

    Andersen, Esben Sloth

    2002-01-01

    The purpose of this paper is to bring forth an interaction between evolutionary economics and industrial systematics. The suggested solution is to reconstruct the "family tree" of the industries. Such a tree is based on similarities, but it may also reflect the evolutionary history in industries....... For this purpose the paper shows how matrices of input-output coefficients can be transformed into binary characteristics matrices and to distance matrices, and it also discusses the possible evolutionary meaning of this translation. Then these derived matrices are used as inputs to algorithms for the heuristic...... finding of optimal industrial trees. The results are presented as taxonomic trees that can easily be compared with the hierarchical structure of existing systems of industrial classification....

  8. Sow-activity classification from acceleration patterns

    DEFF Research Database (Denmark)

    Escalante, Hugo Jair; Rodriguez, Sara V.; Cordero, Jorge

    2013-01-01

    sow-activity classification can be approached with standard machine learning methods for pattern classification. Individual predictions for elements of times series of arbitrary length are combined to classify it as a whole. An extensive comparison of representative learning algorithms, including......This paper describes a supervised learning approach to sow-activity classification from accelerometer measurements. In the proposed methodology, pairs of accelerometer measurements and activity types are considered as labeled instances of a usual supervised classification task. Under this scenario...... neural networks, support vector machines, and ensemble methods, is presented. Experimental results are reported using a data set for sow-activity classification collected in a real production herd. The data set, which has been widely used in related works, includes measurements from active (Feeding...

  9. Shopping intention prediction using decision trees

    Directory of Open Access Journals (Sweden)

    Dario Šebalj

    2017-09-01

    Full Text Available Introduction: The price is considered to be neglected marketing mix element due to the complexity of price management and sensitivity of customers on price changes. It pulls the fastest customer reactions to that change. Accordingly, the process of making shopping decisions can be very challenging for customer. Objective: The aim of this paper is to create a model that is able to predict shopping intention and classify respondents into one of the two categories, depending on whether they intend to shop or not. Methods: Data sample consists of 305 respondents, who are persons older than 18 years involved in buying groceries for their household. The research was conducted in February 2017. In order to create a model, the decision trees method was used with its several classification algorithms. Results: All models, except the one that used RandomTree algorithm, achieved relatively high classification rate (over the 80%. The highest classification accuracy of 84.75% gave J48 and RandomForest algorithms. Since there is no statistically significant difference between those two algorithms, authors decided to choose J48 algorithm and build a decision tree. Conclusions: The value for money and price level in the store were the most significant variables for classification of shopping intention. Future study plans to compare this model with some other data mining techniques, such as neural networks or support vector machines since these techniques achieved very good accuracy in some previous research in this field.

  10. Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries.

    Science.gov (United States)

    Noor, Siti Salwa Md; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

    2017-11-16

    In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability.

  11. Musical Instrument Classification Based on Nonlinear Recurrence Analysis and Supervised Learning

    Directory of Open Access Journals (Sweden)

    R.Rui

    2013-04-01

    Full Text Available In this paper, the phase space reconstruction of time series produced by different instruments is discussed based on the nonlinear dynamic theory. The dense ratio, a novel quantitative recurrence parameter, is proposed to describe the difference of wind instruments, stringed instruments and keyboard instruments in the phase space by analyzing the recursive property of every instrument. Furthermore, a novel supervised learning algorithm for automatic classification of individual musical instrument signals is addressed deriving from the idea of supervised non-negative matrix factorization (NMF algorithm. In our approach, the orthogonal basis matrix could be obtained without updating the matrix iteratively, which NMF is unable to do. The experimental results indicate that the accuracy of the proposed method is improved by 3% comparing with the conventional features in the individual instrument classification.

  12. A comparative study of machine learning models for ethnicity classification

    Science.gov (United States)

    Trivedi, Advait; Bessie Amali, D. Geraldine

    2017-11-01

    This paper endeavours to adopt a machine learning approach to solve the problem of ethnicity recognition. Ethnicity identification is an important vision problem with its use cases being extended to various domains. Despite the multitude of complexity involved, ethnicity identification comes naturally to humans. This meta information can be leveraged to make several decisions, be it in target marketing or security. With the recent development of intelligent systems a sub module to efficiently capture ethnicity would be useful in several use cases. Several attempts to identify an ideal learning model to represent a multi-ethnic dataset have been recorded. A comparative study of classifiers such as support vector machines, logistic regression has been documented. Experimental results indicate that the logical classifier provides a much accurate classification than the support vector machine.

  13. Time series classification using k-Nearest neighbours, Multilayer Perceptron and Learning Vector Quantization algorithms

    Directory of Open Access Journals (Sweden)

    Jiří Fejfar

    2012-01-01

    Full Text Available We are presenting results comparison of three artificial intelligence algorithms in a classification of time series derived from musical excerpts in this paper. Algorithms were chosen to represent different principles of classification – statistic approach, neural networks and competitive learning. The first algorithm is a classical k-Nearest neighbours algorithm, the second algorithm is Multilayer Perceptron (MPL, an example of artificial neural network and the third one is a Learning Vector Quantization (LVQ algorithm representing supervised counterpart to unsupervised Self Organizing Map (SOM.After our own former experiments with unlabelled data we moved forward to the data labels utilization, which generally led to a better accuracy of classification results. As we need huge data set of labelled time series (a priori knowledge of correct class which each time series instance belongs to, we used, with a good experience in former studies, musical excerpts as a source of real-world time series. We are using standard deviation of the sound signal as a descriptor of a musical excerpts volume level.We are describing principle of each algorithm as well as its implementation briefly, giving links for further research. Classification results of each algorithm are presented in a confusion matrix showing numbers of misclassifications and allowing to evaluate overall accuracy of the algorithm. Results are compared and particular misclassifications are discussed for each algorithm. Finally the best solution is chosen and further research goals are given.

  14. Comparison of tree types of models for the prediction of final academic achievement

    Directory of Open Access Journals (Sweden)

    Silvana Gasar

    2002-12-01

    Full Text Available For efficient prevention of inappropriate secondary school choices and by that academic failure, school counselors need a tool for the prediction of individual pupil's final academic achievements. Using data mining techniques on pupils' data base and expert modeling, we developed several models for the prediction of final academic achievement in an individual high school educational program. For data mining, we used statistical analyses, clustering and two machine learning methods: developing classification decision trees and hierarchical decision models. Using an expert system shell DEX, an expert system, based on a hierarchical multi-attribute decision model, was developed manually. All the models were validated and evaluated from the viewpoint of their applicability. The predictive accuracy of DEX models and decision trees was equal and very satisfying, as it reached the predictive accuracy of an experienced counselor. With respect on the efficiency and difficulties in developing models, and relatively rapid changing of our education system, we propose that decision trees are used in further development of predictive models.

  15. Pattern Classification with Memristive Crossbar Circuits

    Science.gov (United States)

    2016-03-31

    Pattern Classification with Memristive Crossbar Circuits Dmitri B. Strukov Department of Electrical and Computer Engineering Department UC Santa...pattern classification ; deep learning; convolutional neural network networks. Introduction Deep-learning convolutional neural networks (DLCNN), which...the best classification performances on a variety of benchmark tasks [1]. The major challenge in building fast and energy- efficient networks of this

  16. Unrealistic phylogenetic trees may improve phylogenetic footprinting.

    Science.gov (United States)

    Nettling, Martin; Treutler, Hendrik; Cerquides, Jesus; Grosse, Ivo

    2017-06-01

    The computational investigation of DNA binding motifs from binding sites is one of the classic tasks in bioinformatics and a prerequisite for understanding gene regulation as a whole. Due to the development of sequencing technologies and the increasing number of available genomes, approaches based on phylogenetic footprinting become increasingly attractive. Phylogenetic footprinting requires phylogenetic trees with attached substitution probabilities for quantifying the evolution of binding sites, but these trees and substitution probabilities are typically not known and cannot be estimated easily. Here, we investigate the influence of phylogenetic trees with different substitution probabilities on the classification performance of phylogenetic footprinting using synthetic and real data. For synthetic data we find that the classification performance is highest when the substitution probability used for phylogenetic footprinting is similar to that used for data generation. For real data, however, we typically find that the classification performance of phylogenetic footprinting surprisingly increases with increasing substitution probabilities and is often highest for unrealistically high substitution probabilities close to one. This finding suggests that choosing realistic model assumptions might not always yield optimal predictions in general and that choosing unrealistically high substitution probabilities close to one might actually improve the classification performance of phylogenetic footprinting. The proposed PF is implemented in JAVA and can be downloaded from https://github.com/mgledi/PhyFoo. : martin.nettling@informatik.uni-halle.de. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press.

  17. Predicting Increased Blood Pressure Using Machine Learning

    Science.gov (United States)

    Golino, Hudson Fernandes; Amaral, Liliany Souza de Brito; Duarte, Stenio Fernando Pimentel; Soares, Telma de Jesus; dos Reis, Luciana Araujo

    2014-01-01

    The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo R 2 (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo R 2 (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power. PMID:24669313

  18. Predicting Increased Blood Pressure Using Machine Learning

    Directory of Open Access Journals (Sweden)

    Hudson Fernandes Golino

    2014-01-01

    Full Text Available The present study investigates the prediction of increased blood pressure by body mass index (BMI, waist (WC and hip circumference (HC, and waist hip ratio (WHR using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42, misclassification (.19, and the higher pseudo R2 (.43. This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25, misclassification (.16, and the higher pseudo R2 (.46. This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

  19. Predicting increased blood pressure using machine learning.

    Science.gov (United States)

    Golino, Hudson Fernandes; Amaral, Liliany Souza de Brito; Duarte, Stenio Fernando Pimentel; Gomes, Cristiano Mauro Assis; Soares, Telma de Jesus; Dos Reis, Luciana Araujo; Santos, Joselito

    2014-01-01

    The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo R (2) (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo R (2) (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

  20. Image-based deep learning for classification of noise transients in gravitational wave detectors

    Science.gov (United States)

    Razzano, Massimiliano; Cuoco, Elena

    2018-05-01

    The detection of gravitational waves has inaugurated the era of gravitational astronomy and opened new avenues for the multimessenger study of cosmic sources. Thanks to their sensitivity, the Advanced LIGO and Advanced Virgo interferometers will probe a much larger volume of space and expand the capability of discovering new gravitational wave emitters. The characterization of these detectors is a primary task in order to recognize the main sources of noise and optimize the sensitivity of interferometers. Glitches are transient noise events that can impact the data quality of the interferometers and their classification is an important task for detector characterization. Deep learning techniques are a promising tool for the recognition and classification of glitches. We present a classification pipeline that exploits convolutional neural networks to classify glitches starting from their time-frequency evolution represented as images. We evaluated the classification accuracy on simulated glitches, showing that the proposed algorithm can automatically classify glitches on very fast timescales and with high accuracy, thus providing a promising tool for online detector characterization.

  1. Recognizing human actions by learning and matching shape-motion prototype trees.

    Science.gov (United States)

    Jiang, Zhuolin; Lin, Zhe; Davis, Larry S

    2012-03-01

    A shape-motion prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences. During training, an action prototype tree is learned in a joint shape and motion space via hierarchical K-means clustering and each training sequence is represented as a labeled prototype sequence; then a look-up table of prototype-to-prototype distances is generated. During testing, based on a joint probability model of the actor location and action prototype, the actor is tracked while a frame-to-prototype correspondence is established by maximizing the joint probability, which is efficiently performed by searching the learned prototype tree; then actions are recognized using dynamic prototype sequence matching. Distance measures used for sequence matching are rapidly obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distances. Our approach enables robust action matching in challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences. Experimental results demonstrate that our approach achieves recognition rates of 92.86 percent on a large gesture data set (with dynamic backgrounds), 100 percent on the Weizmann action data set, 95.77 percent on the KTH action data set, 88 percent on the UCF sports data set, and 87.27 percent on the CMU action data set.

  2. Gene selection and classification for cancer microarray data based on machine learning and similarity measures

    Directory of Open Access Journals (Sweden)

    Liu Qingzhong

    2011-12-01

    Full Text Available Abstract Background Microarray data have a high dimension of variables and a small sample size. In microarray data analyses, two important issues are how to choose genes, which provide reliable and good prediction for disease status, and how to determine the final gene set that is best for classification. Associations among genetic markers mean one can exploit information redundancy to potentially reduce classification cost in terms of time and money. Results To deal with redundant information and improve classification, we propose a gene selection method, Recursive Feature Addition, which combines supervised learning and statistical similarity measures. To determine the final optimal gene set for prediction and classification, we propose an algorithm, Lagging Prediction Peephole Optimization. By using six benchmark microarray gene expression data sets, we compared Recursive Feature Addition with recently developed gene selection methods: Support Vector Machine Recursive Feature Elimination, Leave-One-Out Calculation Sequential Forward Selection and several others. Conclusions On average, with the use of popular learning machines including Nearest Mean Scaled Classifier, Support Vector Machine, Naive Bayes Classifier and Random Forest, Recursive Feature Addition outperformed other methods. Our studies also showed that Lagging Prediction Peephole Optimization is superior to random strategy; Recursive Feature Addition with Lagging Prediction Peephole Optimization obtained better testing accuracies than the gene selection method varSelRF.

  3. [Analysis of dietary pattern and diabetes mellitus influencing factors identified by classification tree model in adults of Fujian].

    Science.gov (United States)

    Yu, F L; Ye, Y; Yan, Y S

    2017-05-10

    Objective: To find out the dietary patterns and explore the relationship between environmental factors (especially dietary patterns) and diabetes mellitus in the adults of Fujian. Methods: Multi-stage sampling method were used to survey residents aged ≥18 years by questionnaire, physical examination and laboratory detection in 10 disease surveillance points in Fujian. Factor analysis was used to identify the dietary patterns, while logistic regression model was applied to analyze relationship between dietary patterns and diabetes mellitus, and classification tree model was adopted to identify the influencing factors for diabetes mellitus. Results: There were four dietary patterns in the population, including meat, plant, high-quality protein, and fried food and beverages patterns. The result of logistic analysis showed that plant pattern, which has higher factor loading of fresh fruit-vegetables and cereal-tubers, was a protective factor for non-diabetes mellitus. The risk of diabetes mellitus in the population at T2 and T3 levels of factor score were 0.727 (95 %CI: 0.561-0.943) times and 0.736 (95 %CI : 0.573-0.944) times higher, respectively, than those whose factor score was in lowest quartile. Thirteen influencing factors and eleven group at high-risk for diabetes mellitus were identified by classification tree model. The influencing factors were dyslipidemia, age, family history of diabetes, hypertension, physical activity, career, sex, sedentary time, abdominal adiposity, BMI, marital status, sleep time and high-quality protein pattern. Conclusion: There is a close association between dietary patterns and diabetes mellitus. It is necessary to promote healthy and reasonable diet, strengthen the monitoring and control of blood lipids, blood pressure and body weight, and have good lifestyle for the prevention and control of diabetes mellitus.

  4. Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network.

    Science.gov (United States)

    Guo, Hao; Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

    2017-01-01

    High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

  5. A Branch-and-Price approach to find optimal decision trees

    NARCIS (Netherlands)

    Firat, M.; Crognier, Guillaume; Gabor, Adriana; Zhang, Y.

    2018-01-01

    In Artificial Intelligence (AI) field, decision trees have gained certain importance due to their effectiveness in solving classification and regression problems. Recently, in the literature we see finding optimal decision trees are formulated as Mixed Integer Linear Programming (MILP) models. This

  6. Information-Theoretic Data Discarding for Dynamic Trees on Data Streams

    Directory of Open Access Journals (Sweden)

    Christoforos Anagnostopoulos

    2013-12-01

    Full Text Available Ubiquitous automated data collection at an unprecedented scale is making available streaming, real-time information flows in a wide variety of settings, transforming both science and industry. Learning algorithms deployed in such contexts often rely on single-pass inference, where the data history is never revisited. Learning may also need to be temporally adaptive to remain up-to-date against unforeseen changes in the data generating mechanism. Online Bayesian inference remains challenged by such transient, evolving data streams. Nonparametric modeling techniques can prove particularly ill-suited, as the complexity of the model is allowed to increase with the sample size. In this work, we take steps to overcome these challenges by porting information theoretic heuristics, such as exponential forgetting and active learning, into a fully Bayesian framework. We showcase our methods by augmenting a modern non-parametric modeling framework, dynamic trees, and illustrate its performance on a number of practical examples. The end product is a powerful streaming regression and classification tool, whose performance compares favorably to the state-of-the-art.

  7. Poster abstract: A machine learning approach for vehicle classification using passive infrared and ultrasonic sensors

    KAUST Repository

    Warriach, Ehsan Ullah; Claudel, Christian G.

    2013-01-01

    This article describes the implementation of four different machine learning techniques for vehicle classification in a dual ultrasonic/passive infrared traffic flow sensors. Using k-NN, Naive Bayes, SVM and KNN-SVM algorithms, we show that KNN

  8. Learning Supervised Topic Models for Classification and Regression from Crowds.

    Science.gov (United States)

    Rodrigues, Filipe; Lourenco, Mariana; Ribeiro, Bernardete; Pereira, Francisco C

    2017-12-01

    The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state-of-the-art approaches.

  9. Traditional Chinese medicine pharmacovigilance in signal detection: decision tree-based data classification.

    Science.gov (United States)

    Wei, Jian-Xiang; Wang, Jing; Zhu, Yun-Xia; Sun, Jun; Xu, Hou-Ming; Li, Ming

    2018-03-09

    Traditional Chinese Medicine (TCM) is a style of traditional medicine informed by modern medicine but built on a foundation of more than 2500 years of Chinese medical practice. According to statistics, TCM accounts for approximately 14% of total adverse drug reaction (ADR) spontaneous reporting data in China. Because of the complexity of the components in TCM formula, which makes it essentially different from Western medicine, it is critical to determine whether ADR reports of TCM should be analyzed independently. Reports in the Chinese spontaneous reporting database between 2010 and 2011 were selected. The dataset was processed and divided into the total sample (all data) and the subsample (including TCM data only). Four different ADR signal detection methods-PRR, ROR, MHRA and IC- currently widely used in China, were applied for signal detection on the two samples. By comparison of experimental results, three of them-PRR, MHRA and IC-were chosen to do the experiment. We designed several indicators for performance evaluation such as R (recall ratio), P (precision ratio), and D (discrepancy ratio) based on the reference database and then constructed a decision tree for data classification based on such indicators. For PRR: R 1 -R 2  = 0.72%, P 1 -P 2  = 0.16% and D = 0.92%; For MHRA: R 1 -R 2  = 0.97%, P 1 -P 2  = 0.20% and D = 1.18%; For IC: R 1 -R 2  = 1.44%, P 2 -P 1  = 4.06% and D = 4.72%. The threshold of R,Pand Dis set as 2%, 2% and 3% respectively. Based on the decision tree, the results are "separation" for PRR, MHRA and IC. In order to improve the efficiency and accuracy of signal detection, we suggest that TCM data should be separated from the total sample when conducting analyses.

  10. Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

    Science.gov (United States)

    Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

    2018-01-05

    Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

  11. Task-Driven Dictionary Learning Based on Mutual Information for Medical Image Classification.

    Science.gov (United States)

    Diamant, Idit; Klang, Eyal; Amitai, Michal; Konen, Eli; Goldberger, Jacob; Greenspan, Hayit

    2017-06-01

    We present a novel variant of the bag-of-visual-words (BoVW) method for automated medical image classification. Our approach improves the BoVW model by learning a task-driven dictionary of the most relevant visual words per task using a mutual information-based criterion. Additionally, we generate relevance maps to visualize and localize the decision of the automatic classification algorithm. These maps demonstrate how the algorithm works and show the spatial layout of the most relevant words. We applied our algorithm to three different tasks: chest x-ray pathology identification (of four pathologies: cardiomegaly, enlarged mediastinum, right consolidation, and left consolidation), liver lesion classification into four categories in computed tomography (CT) images and benign/malignant clusters of microcalcifications (MCs) classification in breast mammograms. Validation was conducted on three datasets: 443 chest x-rays, 118 portal phase CT images of liver lesions, and 260 mammography MCs. The proposed method improves the classical BoVW method for all tested applications. For chest x-ray, area under curve of 0.876 was obtained for enlarged mediastinum identification compared to 0.855 using classical BoVW (with p-value 0.01). For MC classification, a significant improvement of 4% was achieved using our new approach (with p-value = 0.03). For liver lesion classification, an improvement of 6% in sensitivity and 2% in specificity were obtained (with p-value 0.001). We demonstrated that classification based on informative selected set of words results in significant improvement. Our new BoVW approach shows promising results in clinically important domains. Additionally, it can discover relevant parts of images for the task at hand without explicit annotations for training data. This can provide computer-aided support for medical experts in challenging image analysis tasks.

  12. Learning with distribution of optimized features for recognizing common CT imaging signs of lung diseases

    Science.gov (United States)

    Ma, Ling; Liu, Xiabi; Fei, Baowei

    2017-01-01

    Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients. CISLs play important roles in the diagnosis of lung diseases. This paper proposes a novel learning method, namely learning with distribution of optimized feature (DOF), to effectively recognize the characteristics of CISLs. We improve the classification performance by learning the optimized features under different distributions. Specifically, we adopt the minimum spanning tree algorithm to capture the relationship between features and discriminant ability of features for selecting the most important features. To overcome the problem of various distributions in one CISL, we propose a hierarchical learning method. First, we use an unsupervised learning method to cluster samples into groups based on their distribution. Second, in each group, we use a supervised learning method to train a model based on their categories of CISLs. Finally, we obtain multiple classification decisions from multiple trained models and use majority voting to achieve the final decision. The proposed approach has been implemented on a set of 511 samples captured from human lung CT images and achieves a classification accuracy of 91.96%. The proposed DOF method is effective and can provide a useful tool for computer-aided diagnosis of lung diseases on CT images.

  13. An Analysis of Machine- and Human-Analytics in Classification.

    Science.gov (United States)

    Tam, Gary K L; Kothari, Vivek; Chen, Min

    2017-01-01

    In this work, we present a study that traces the technical and cognitive processes in two visual analytics applications to a common theoretic model of soft knowledge that may be added into a visual analytics process for constructing a decision-tree model. Both case studies involved the development of classification models based on the "bag of features" approach. Both compared a visual analytics approach using parallel coordinates with a machine-learning approach using information theory. Both found that the visual analytics approach had some advantages over the machine learning approach, especially when sparse datasets were used as the ground truth. We examine various possible factors that may have contributed to such advantages, and collect empirical evidence for supporting the observation and reasoning of these factors. We propose an information-theoretic model as a common theoretic basis to explain the phenomena exhibited in these two case studies. Together we provide interconnected empirical and theoretical evidence to support the usefulness of visual analytics.

  14. Comparison of Single and Multi-Scale Method for Leaf and Wood Points Classification from Terrestrial Laser Scanning Data

    Science.gov (United States)

    Wei, Hongqiang; Zhou, Guiyun; Zhou, Junjie

    2018-04-01

    The classification of leaf and wood points is an essential preprocessing step for extracting inventory measurements and canopy characterization of trees from the terrestrial laser scanning (TLS) data. The geometry-based approach is one of the widely used classification method. In the geometry-based method, it is common practice to extract salient features at one single scale before the features are used for classification. It remains unclear how different scale(s) used affect the classification accuracy and efficiency. To assess the scale effect on the classification accuracy and efficiency, we extracted the single-scale and multi-scale salient features from the point clouds of two oak trees of different sizes and conducted the classification on leaf and wood. Our experimental results show that the balanced accuracy of the multi-scale method is higher than the average balanced accuracy of the single-scale method by about 10 % for both trees. The average speed-up ratio of single scale classifiers over multi-scale classifier for each tree is higher than 30.

  15. The classification problem in machine learning: an overview with study cases in emotion recognition and music-speech differentiation

    OpenAIRE

    Rodríguez Cadavid, Santiago

    2015-01-01

    This work addresses the well-known classification problem in machine learning -- The goal of this study is to approach the reader to the methodological aspects of the feature extraction, feature selection and classifier performance through simple and understandable theoretical aspects and two study cases -- Finally, a very good classification performance was obtained for the emotion recognition from speech

  16. Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

    Directory of Open Access Journals (Sweden)

    Liu Ying

    2017-01-01

    Full Text Available Ship detection and classification is critical for national maritime security and national defense. Although some SAR (Synthetic Aperture Radar image-based ship detection approaches have been proposed and used, they are not able to satisfy the requirement of real-world applications as the number of SAR sensors is limited, the resolution is low, and the revisit cycle is long. As massive optical remote sensing images of high resolution are available, ship detection and classification on theses images is becoming a promising technique, and has attracted great attention on applications including maritime security and traffic control. Some digital image processing methods have been proposed to detect ships in optical remote sensing images, but most of them face difficulty in terms of accuracy, performance and complexity. Recently, an autoencoder-based deep neural network with extreme learning machine was proposed, but it cannot meet the requirement of real-world applications as it only works with simple and small-scaled data sets. Therefore, in this paper, we propose a novel ship detection and classification approach which utilizes deep convolutional neural network (CNN as the ship classifier. The performance of our proposed ship detection and classification approach was evaluated on a set of images downloaded from Google Earth at the resolution 0.5m. 99% detection accuracy and 95% classification accuracy were achieved. In model training, 75× speedup is achieved on 1 Nvidia Titanx GPU.

  17. Deep-learning derived features for lung nodule classification with limited datasets

    Science.gov (United States)

    Thammasorn, P.; Wu, W.; Pierce, L. A.; Pipavath, S. N.; Lampe, P. D.; Houghton, A. M.; Haynor, D. R.; Chaovalitwongse, W. A.; Kinahan, P. E.

    2018-02-01

    Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

  18. Research into Financial Position of Listed Companies following Classification via Extreme Learning Machine Based upon DE Optimization

    OpenAIRE

    Fu Yu; Mu Jiong; Duan Xu Liang

    2016-01-01

    By means of the model of extreme learning machine based upon DE optimization, this article particularly centers on the optimization thinking of such a model as well as its application effect in the field of listed company’s financial position classification. It proves that the improved extreme learning machine algorithm based upon DE optimization eclipses the traditional extreme learning machine algorithm following comparison. Meanwhile, this article also intends to introduce certain research...

  19. Voxel-Based Neighborhood for Spatial Shape Pattern Classification of Lidar Point Clouds with Supervised Learning

    Directory of Open Access Journals (Sweden)

    Victoria Plaza-Leiva

    2017-03-01

    Full Text Available Improving the effectiveness of spatial shape features classification from 3D lidar data is very relevant because it is largely used as a fundamental step towards higher level scene understanding challenges of autonomous vehicles and terrestrial robots. In this sense, computing neighborhood for points in dense scans becomes a costly process for both training and classification. This paper proposes a new general framework for implementing and comparing different supervised learning classifiers with a simple voxel-based neighborhood computation where points in each non-overlapping voxel in a regular grid are assigned to the same class by considering features within a support region defined by the voxel itself. The contribution provides offline training and online classification procedures as well as five alternative feature vector definitions based on principal component analysis for scatter, tubular and planar shapes. Moreover, the feasibility of this approach is evaluated by implementing a neural network (NN method previously proposed by the authors as well as three other supervised learning classifiers found in scene processing methods: support vector machines (SVM, Gaussian processes (GP, and Gaussian mixture models (GMM. A comparative performance analysis is presented using real point clouds from both natural and urban environments and two different 3D rangefinders (a tilting Hokuyo UTM-30LX and a Riegl. Classification performance metrics and processing time measurements confirm the benefits of the NN classifier and the feasibility of voxel-based neighborhood.

  20. Voxel-Based Neighborhood for Spatial Shape Pattern Classification of Lidar Point Clouds with Supervised Learning.

    Science.gov (United States)

    Plaza-Leiva, Victoria; Gomez-Ruiz, Jose Antonio; Mandow, Anthony; García-Cerezo, Alfonso

    2017-03-15

    Improving the effectiveness of spatial shape features classification from 3D lidar data is very relevant because it is largely used as a fundamental step towards higher level scene understanding challenges of autonomous vehicles and terrestrial robots. In this sense, computing neighborhood for points in dense scans becomes a costly process for both training and classification. This paper proposes a new general framework for implementing and comparing different supervised learning classifiers with a simple voxel-based neighborhood computation where points in each non-overlapping voxel in a regular grid are assigned to the same class by considering features within a support region defined by the voxel itself. The contribution provides offline training and online classification procedures as well as five alternative feature vector definitions based on principal component analysis for scatter, tubular and planar shapes. Moreover, the feasibility of this approach is evaluated by implementing a neural network (NN) method previously proposed by the authors as well as three other supervised learning classifiers found in scene processing methods: support vector machines (SVM), Gaussian processes (GP), and Gaussian mixture models (GMM). A comparative performance analysis is presented using real point clouds from both natural and urban environments and two different 3D rangefinders (a tilting Hokuyo UTM-30LX and a Riegl). Classification performance metrics and processing time measurements confirm the benefits of the NN classifier and the feasibility of voxel-based neighborhood.